Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-570/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: transformers
+model_name: weights_4
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for weights_4
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.19.0
+- Transformers: 4.53.0
+- Pytorch: 2.7.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-500/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-500/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-500/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.0"
+}

checkpoint-500/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2b025eb9ec6d742f73d319d387f54b91476a5d5bb00a4588d1fd2dcb87d369
+size 4972454376

checkpoint-500/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79d1d181a0e6ceda9c2ee8ab6e605c18485f6b741dbc5789e2f4036c026025c
+size 4832048608

checkpoint-500/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65a580d9ec401aa47414315a6ab7e40ac5b4a78f91c0707991b13c7cb9d9e03
+size 3462482728

checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 32762941440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2534e434cd5abbb8f7668d3eab0549db0ef95d6a797a3efa86b712e8e32266a7
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae9e2440856d0a3ab8ef9d108eae199f62a18cdec8eedf480cefde2044df26a
+size 1465

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6315789473684212,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 5.827399730682373,
+      "learning_rate": 1.968421052631579e-05,
+      "loss": 1.8455,
+      "mean_token_accuracy": 0.5674484133720398,
+      "num_tokens": 11541.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 4.475362300872803,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 1.5323,
+      "mean_token_accuracy": 0.6094174444675445,
+      "num_tokens": 22649.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 4.522463321685791,
+      "learning_rate": 1.898245614035088e-05,
+      "loss": 1.5459,
+      "mean_token_accuracy": 0.6038810610771179,
+      "num_tokens": 33775.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 4.1712775230407715,
+      "learning_rate": 1.8631578947368424e-05,
+      "loss": 1.5167,
+      "mean_token_accuracy": 0.611203521490097,
+      "num_tokens": 45182.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 4.325103759765625,
+      "learning_rate": 1.8280701754385966e-05,
+      "loss": 1.5465,
+      "mean_token_accuracy": 0.6018322885036469,
+      "num_tokens": 56080.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 3.4913244247436523,
+      "learning_rate": 1.792982456140351e-05,
+      "loss": 1.4975,
+      "mean_token_accuracy": 0.6165669798851013,
+      "num_tokens": 67393.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 3.657413959503174,
+      "learning_rate": 1.7578947368421054e-05,
+      "loss": 1.4742,
+      "mean_token_accuracy": 0.6143243193626404,
+      "num_tokens": 78542.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.5924668312072754,
+      "learning_rate": 1.72280701754386e-05,
+      "loss": 1.5084,
+      "mean_token_accuracy": 0.608461570739746,
+      "num_tokens": 89963.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 3.244269609451294,
+      "learning_rate": 1.687719298245614e-05,
+      "loss": 1.4668,
+      "mean_token_accuracy": 0.6215168476104737,
+      "num_tokens": 101761.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 3.2805733680725098,
+      "learning_rate": 1.6526315789473686e-05,
+      "loss": 1.5016,
+      "mean_token_accuracy": 0.6094469010829926,
+      "num_tokens": 112833.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 3.5279650688171387,
+      "learning_rate": 1.6175438596491228e-05,
+      "loss": 1.4591,
+      "mean_token_accuracy": 0.6197056353092194,
+      "num_tokens": 123982.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 3.697514057159424,
+      "learning_rate": 1.5824561403508774e-05,
+      "loss": 1.4903,
+      "mean_token_accuracy": 0.6157862544059753,
+      "num_tokens": 135281.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 3.5749077796936035,
+      "learning_rate": 1.5473684210526316e-05,
+      "loss": 1.4905,
+      "mean_token_accuracy": 0.6141646564006805,
+      "num_tokens": 146813.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 3.9152824878692627,
+      "learning_rate": 1.5122807017543861e-05,
+      "loss": 1.4288,
+      "mean_token_accuracy": 0.6200086832046509,
+      "num_tokens": 157970.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 3.2869362831115723,
+      "learning_rate": 1.4771929824561405e-05,
+      "loss": 1.4484,
+      "mean_token_accuracy": 0.6214825510978699,
+      "num_tokens": 169217.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 3.530872106552124,
+      "learning_rate": 1.4421052631578948e-05,
+      "loss": 1.4638,
+      "mean_token_accuracy": 0.6164202988147736,
+      "num_tokens": 180220.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 3.1449363231658936,
+      "learning_rate": 1.4070175438596492e-05,
+      "loss": 1.4679,
+      "mean_token_accuracy": 0.6190443515777588,
+      "num_tokens": 192002.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 3.275167942047119,
+      "learning_rate": 1.3719298245614037e-05,
+      "loss": 1.421,
+      "mean_token_accuracy": 0.6280941605567932,
+      "num_tokens": 203462.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.7444939613342285,
+      "learning_rate": 1.336842105263158e-05,
+      "loss": 1.4532,
+      "mean_token_accuracy": 0.6205313920974731,
+      "num_tokens": 214070.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 3.492197275161743,
+      "learning_rate": 1.3017543859649125e-05,
+      "loss": 0.8224,
+      "mean_token_accuracy": 0.7620033979415893,
+      "num_tokens": 225485.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 2.8766427040100098,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 0.7886,
+      "mean_token_accuracy": 0.7641067266464233,
+      "num_tokens": 236739.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 3.0320887565612793,
+      "learning_rate": 1.2315789473684212e-05,
+      "loss": 0.7586,
+      "mean_token_accuracy": 0.7756024956703186,
+      "num_tokens": 248217.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 3.0771596431732178,
+      "learning_rate": 1.1964912280701754e-05,
+      "loss": 0.8016,
+      "mean_token_accuracy": 0.7638419806957245,
+      "num_tokens": 259404.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 3.5975608825683594,
+      "learning_rate": 1.16140350877193e-05,
+      "loss": 0.7888,
+      "mean_token_accuracy": 0.7639639139175415,
+      "num_tokens": 270555.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 3.4842450618743896,
+      "learning_rate": 1.1263157894736843e-05,
+      "loss": 0.7854,
+      "mean_token_accuracy": 0.7633719563484191,
+      "num_tokens": 281976.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 3.1366794109344482,
+      "learning_rate": 1.0912280701754387e-05,
+      "loss": 0.7904,
+      "mean_token_accuracy": 0.7618038773536682,
+      "num_tokens": 293356.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 3.246885299682617,
+      "learning_rate": 1.056140350877193e-05,
+      "loss": 0.7745,
+      "mean_token_accuracy": 0.7625904023647309,
+      "num_tokens": 304686.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 3.398383140563965,
+      "learning_rate": 1.0210526315789476e-05,
+      "loss": 0.8135,
+      "mean_token_accuracy": 0.7576355338096619,
+      "num_tokens": 315735.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 3.1334409713745117,
+      "learning_rate": 9.859649122807018e-06,
+      "loss": 0.8007,
+      "mean_token_accuracy": 0.7634194076061249,
+      "num_tokens": 326982.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 3.123152017593384,
+      "learning_rate": 9.508771929824562e-06,
+      "loss": 0.7878,
+      "mean_token_accuracy": 0.7639511227607727,
+      "num_tokens": 338160.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 3.388254404067993,
+      "learning_rate": 9.157894736842105e-06,
+      "loss": 0.7935,
+      "mean_token_accuracy": 0.7603401899337768,
+      "num_tokens": 349306.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 3.4574532508850098,
+      "learning_rate": 8.807017543859649e-06,
+      "loss": 0.7912,
+      "mean_token_accuracy": 0.759734469652176,
+      "num_tokens": 360346.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 2.8878493309020996,
+      "learning_rate": 8.456140350877193e-06,
+      "loss": 0.7664,
+      "mean_token_accuracy": 0.7666481971740723,
+      "num_tokens": 371823.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 3.632908582687378,
+      "learning_rate": 8.105263157894736e-06,
+      "loss": 0.7792,
+      "mean_token_accuracy": 0.7634695649147034,
+      "num_tokens": 383113.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 3.0787177085876465,
+      "learning_rate": 7.754385964912282e-06,
+      "loss": 0.7973,
+      "mean_token_accuracy": 0.759224247932434,
+      "num_tokens": 394349.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 3.434131622314453,
+      "learning_rate": 7.4035087719298246e-06,
+      "loss": 0.7968,
+      "mean_token_accuracy": 0.7612445116043091,
+      "num_tokens": 405857.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 4.3988871574401855,
+      "learning_rate": 7.052631578947369e-06,
+      "loss": 0.7902,
+      "mean_token_accuracy": 0.7641420245170594,
+      "num_tokens": 416942.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.871621131896973,
+      "learning_rate": 6.701754385964913e-06,
+      "loss": 0.7826,
+      "mean_token_accuracy": 0.763578999042511,
+      "num_tokens": 428140.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 3.33593487739563,
+      "learning_rate": 6.3508771929824565e-06,
+      "loss": 0.3547,
+      "mean_token_accuracy": 0.8930943846702576,
+      "num_tokens": 439280.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 3.4659924507141113,
+      "learning_rate": 6e-06,
+      "loss": 0.3274,
+      "mean_token_accuracy": 0.8942540287971497,
+      "num_tokens": 450443.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 3.334516763687134,
+      "learning_rate": 5.649122807017544e-06,
+      "loss": 0.2965,
+      "mean_token_accuracy": 0.9032998859882355,
+      "num_tokens": 461774.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 3.0437450408935547,
+      "learning_rate": 5.298245614035088e-06,
+      "loss": 0.2991,
+      "mean_token_accuracy": 0.9052271246910095,
+      "num_tokens": 473068.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 3.4685380458831787,
+      "learning_rate": 4.947368421052632e-06,
+      "loss": 0.3096,
+      "mean_token_accuracy": 0.900404566526413,
+      "num_tokens": 484122.0,
+      "step": 430
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 3.8948161602020264,
+      "learning_rate": 4.596491228070176e-06,
+      "loss": 0.2997,
+      "mean_token_accuracy": 0.901084166765213,
+      "num_tokens": 495492.0,
+      "step": 440
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 3.75742506980896,
+      "learning_rate": 4.245614035087719e-06,
+      "loss": 0.3066,
+      "mean_token_accuracy": 0.901238763332367,
+      "num_tokens": 507138.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 3.1433157920837402,
+      "learning_rate": 3.894736842105263e-06,
+      "loss": 0.3153,
+      "mean_token_accuracy": 0.899943882226944,
+      "num_tokens": 518246.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 3.025437831878662,
+      "learning_rate": 3.543859649122807e-06,
+      "loss": 0.2975,
+      "mean_token_accuracy": 0.9012304186820984,
+      "num_tokens": 529617.0,
+      "step": 470
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 3.873894453048706,
+      "learning_rate": 3.192982456140351e-06,
+      "loss": 0.2858,
+      "mean_token_accuracy": 0.9065197288990021,
+      "num_tokens": 540576.0,
+      "step": 480
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 3.2669241428375244,
+      "learning_rate": 2.842105263157895e-06,
+      "loss": 0.2911,
+      "mean_token_accuracy": 0.9069616377353669,
+      "num_tokens": 552038.0,
+      "step": 490
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 3.070552110671997,
+      "learning_rate": 2.4912280701754387e-06,
+      "loss": 0.2875,
+      "mean_token_accuracy": 0.9050689458847045,
+      "num_tokens": 563396.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 570,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.394575181929677e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffaee687bcf434da66f399553b6e3a647d1ffa26a027aa9caf4841c6cfe086c
+size 6161

checkpoint-570/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-570/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-570/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-570/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.0"
+}

checkpoint-570/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2377228dac033fa3ab97988d1c941a87c54a9374043c8325613c46dee547ab60
+size 4972454376

checkpoint-570/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c183a54b2f94bab76c992036ec9d20e8edfcd7752711f5ae889cc69f5f36ba
+size 3462482728

checkpoint-570/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 32762941440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-570/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2534e434cd5abbb8f7668d3eab0549db0ef95d6a797a3efa86b712e8e32266a7
+size 14645

checkpoint-570/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba91c5ffb5111b00b446be9dd68abfffd444b80c59c8a6f2ffb343727fdee5bc
+size 1465

checkpoint-570/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-570/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-570/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-570/trainer_state.json

@@ -0,0 +1,547 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 570,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 5.827399730682373,
+      "learning_rate": 1.968421052631579e-05,
+      "loss": 1.8455,
+      "mean_token_accuracy": 0.5674484133720398,
+      "num_tokens": 11541.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 4.475362300872803,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 1.5323,
+      "mean_token_accuracy": 0.6094174444675445,
+      "num_tokens": 22649.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 4.522463321685791,
+      "learning_rate": 1.898245614035088e-05,
+      "loss": 1.5459,
+      "mean_token_accuracy": 0.6038810610771179,
+      "num_tokens": 33775.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 4.1712775230407715,
+      "learning_rate": 1.8631578947368424e-05,
+      "loss": 1.5167,
+      "mean_token_accuracy": 0.611203521490097,
+      "num_tokens": 45182.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 4.325103759765625,
+      "learning_rate": 1.8280701754385966e-05,
+      "loss": 1.5465,
+      "mean_token_accuracy": 0.6018322885036469,
+      "num_tokens": 56080.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 3.4913244247436523,
+      "learning_rate": 1.792982456140351e-05,
+      "loss": 1.4975,
+      "mean_token_accuracy": 0.6165669798851013,
+      "num_tokens": 67393.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 3.657413959503174,
+      "learning_rate": 1.7578947368421054e-05,
+      "loss": 1.4742,
+      "mean_token_accuracy": 0.6143243193626404,
+      "num_tokens": 78542.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.5924668312072754,
+      "learning_rate": 1.72280701754386e-05,
+      "loss": 1.5084,
+      "mean_token_accuracy": 0.608461570739746,
+      "num_tokens": 89963.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 3.244269609451294,
+      "learning_rate": 1.687719298245614e-05,
+      "loss": 1.4668,
+      "mean_token_accuracy": 0.6215168476104737,
+      "num_tokens": 101761.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 3.2805733680725098,
+      "learning_rate": 1.6526315789473686e-05,
+      "loss": 1.5016,
+      "mean_token_accuracy": 0.6094469010829926,
+      "num_tokens": 112833.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 3.5279650688171387,
+      "learning_rate": 1.6175438596491228e-05,
+      "loss": 1.4591,
+      "mean_token_accuracy": 0.6197056353092194,
+      "num_tokens": 123982.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 3.697514057159424,
+      "learning_rate": 1.5824561403508774e-05,
+      "loss": 1.4903,
+      "mean_token_accuracy": 0.6157862544059753,
+      "num_tokens": 135281.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 3.5749077796936035,
+      "learning_rate": 1.5473684210526316e-05,
+      "loss": 1.4905,
+      "mean_token_accuracy": 0.6141646564006805,
+      "num_tokens": 146813.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 3.9152824878692627,
+      "learning_rate": 1.5122807017543861e-05,
+      "loss": 1.4288,
+      "mean_token_accuracy": 0.6200086832046509,
+      "num_tokens": 157970.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 3.2869362831115723,
+      "learning_rate": 1.4771929824561405e-05,
+      "loss": 1.4484,
+      "mean_token_accuracy": 0.6214825510978699,
+      "num_tokens": 169217.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 3.530872106552124,
+      "learning_rate": 1.4421052631578948e-05,
+      "loss": 1.4638,
+      "mean_token_accuracy": 0.6164202988147736,
+      "num_tokens": 180220.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 3.1449363231658936,
+      "learning_rate": 1.4070175438596492e-05,
+      "loss": 1.4679,
+      "mean_token_accuracy": 0.6190443515777588,
+      "num_tokens": 192002.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 3.275167942047119,
+      "learning_rate": 1.3719298245614037e-05,
+      "loss": 1.421,
+      "mean_token_accuracy": 0.6280941605567932,
+      "num_tokens": 203462.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.7444939613342285,
+      "learning_rate": 1.336842105263158e-05,
+      "loss": 1.4532,
+      "mean_token_accuracy": 0.6205313920974731,
+      "num_tokens": 214070.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 3.492197275161743,
+      "learning_rate": 1.3017543859649125e-05,
+      "loss": 0.8224,
+      "mean_token_accuracy": 0.7620033979415893,
+      "num_tokens": 225485.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 2.8766427040100098,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 0.7886,
+      "mean_token_accuracy": 0.7641067266464233,
+      "num_tokens": 236739.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 3.0320887565612793,
+      "learning_rate": 1.2315789473684212e-05,
+      "loss": 0.7586,
+      "mean_token_accuracy": 0.7756024956703186,
+      "num_tokens": 248217.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 3.0771596431732178,
+      "learning_rate": 1.1964912280701754e-05,
+      "loss": 0.8016,
+      "mean_token_accuracy": 0.7638419806957245,
+      "num_tokens": 259404.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 3.5975608825683594,
+      "learning_rate": 1.16140350877193e-05,
+      "loss": 0.7888,
+      "mean_token_accuracy": 0.7639639139175415,
+      "num_tokens": 270555.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 3.4842450618743896,
+      "learning_rate": 1.1263157894736843e-05,
+      "loss": 0.7854,
+      "mean_token_accuracy": 0.7633719563484191,
+      "num_tokens": 281976.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 3.1366794109344482,
+      "learning_rate": 1.0912280701754387e-05,
+      "loss": 0.7904,
+      "mean_token_accuracy": 0.7618038773536682,
+      "num_tokens": 293356.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 3.246885299682617,
+      "learning_rate": 1.056140350877193e-05,
+      "loss": 0.7745,
+      "mean_token_accuracy": 0.7625904023647309,
+      "num_tokens": 304686.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 3.398383140563965,
+      "learning_rate": 1.0210526315789476e-05,
+      "loss": 0.8135,
+      "mean_token_accuracy": 0.7576355338096619,
+      "num_tokens": 315735.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 3.1334409713745117,
+      "learning_rate": 9.859649122807018e-06,
+      "loss": 0.8007,
+      "mean_token_accuracy": 0.7634194076061249,
+      "num_tokens": 326982.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 3.123152017593384,
+      "learning_rate": 9.508771929824562e-06,
+      "loss": 0.7878,
+      "mean_token_accuracy": 0.7639511227607727,
+      "num_tokens": 338160.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 3.388254404067993,
+      "learning_rate": 9.157894736842105e-06,
+      "loss": 0.7935,
+      "mean_token_accuracy": 0.7603401899337768,
+      "num_tokens": 349306.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 3.4574532508850098,
+      "learning_rate": 8.807017543859649e-06,
+      "loss": 0.7912,
+      "mean_token_accuracy": 0.759734469652176,
+      "num_tokens": 360346.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 2.8878493309020996,
+      "learning_rate": 8.456140350877193e-06,
+      "loss": 0.7664,
+      "mean_token_accuracy": 0.7666481971740723,
+      "num_tokens": 371823.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 3.632908582687378,
+      "learning_rate": 8.105263157894736e-06,
+      "loss": 0.7792,
+      "mean_token_accuracy": 0.7634695649147034,
+      "num_tokens": 383113.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 3.0787177085876465,
+      "learning_rate": 7.754385964912282e-06,
+      "loss": 0.7973,
+      "mean_token_accuracy": 0.759224247932434,
+      "num_tokens": 394349.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 3.434131622314453,
+      "learning_rate": 7.4035087719298246e-06,
+      "loss": 0.7968,
+      "mean_token_accuracy": 0.7612445116043091,
+      "num_tokens": 405857.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 4.3988871574401855,
+      "learning_rate": 7.052631578947369e-06,
+      "loss": 0.7902,
+      "mean_token_accuracy": 0.7641420245170594,
+      "num_tokens": 416942.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.871621131896973,
+      "learning_rate": 6.701754385964913e-06,
+      "loss": 0.7826,
+      "mean_token_accuracy": 0.763578999042511,
+      "num_tokens": 428140.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 3.33593487739563,
+      "learning_rate": 6.3508771929824565e-06,
+      "loss": 0.3547,
+      "mean_token_accuracy": 0.8930943846702576,
+      "num_tokens": 439280.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 3.4659924507141113,
+      "learning_rate": 6e-06,
+      "loss": 0.3274,
+      "mean_token_accuracy": 0.8942540287971497,
+      "num_tokens": 450443.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 3.334516763687134,
+      "learning_rate": 5.649122807017544e-06,
+      "loss": 0.2965,
+      "mean_token_accuracy": 0.9032998859882355,
+      "num_tokens": 461774.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 3.0437450408935547,
+      "learning_rate": 5.298245614035088e-06,
+      "loss": 0.2991,
+      "mean_token_accuracy": 0.9052271246910095,
+      "num_tokens": 473068.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 3.4685380458831787,
+      "learning_rate": 4.947368421052632e-06,
+      "loss": 0.3096,
+      "mean_token_accuracy": 0.900404566526413,
+      "num_tokens": 484122.0,
+      "step": 430
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 3.8948161602020264,
+      "learning_rate": 4.596491228070176e-06,
+      "loss": 0.2997,
+      "mean_token_accuracy": 0.901084166765213,
+      "num_tokens": 495492.0,
+      "step": 440
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 3.75742506980896,
+      "learning_rate": 4.245614035087719e-06,
+      "loss": 0.3066,
+      "mean_token_accuracy": 0.901238763332367,
+      "num_tokens": 507138.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 3.1433157920837402,
+      "learning_rate": 3.894736842105263e-06,
+      "loss": 0.3153,
+      "mean_token_accuracy": 0.899943882226944,
+      "num_tokens": 518246.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 3.025437831878662,
+      "learning_rate": 3.543859649122807e-06,
+      "loss": 0.2975,
+      "mean_token_accuracy": 0.9012304186820984,
+      "num_tokens": 529617.0,
+      "step": 470
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 3.873894453048706,
+      "learning_rate": 3.192982456140351e-06,
+      "loss": 0.2858,
+      "mean_token_accuracy": 0.9065197288990021,
+      "num_tokens": 540576.0,
+      "step": 480
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 3.2669241428375244,
+      "learning_rate": 2.842105263157895e-06,
+      "loss": 0.2911,
+      "mean_token_accuracy": 0.9069616377353669,
+      "num_tokens": 552038.0,
+      "step": 490
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 3.070552110671997,
+      "learning_rate": 2.4912280701754387e-06,
+      "loss": 0.2875,
+      "mean_token_accuracy": 0.9050689458847045,
+      "num_tokens": 563396.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 3.8535304069519043,
+      "learning_rate": 2.1403508771929828e-06,
+      "loss": 0.3166,
+      "mean_token_accuracy": 0.8962113857269287,
+      "num_tokens": 574901.0,
+      "step": 510
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 3.335392951965332,
+      "learning_rate": 1.7894736842105265e-06,
+      "loss": 0.2991,
+      "mean_token_accuracy": 0.9042251408100128,
+      "num_tokens": 586440.0,
+      "step": 520
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 3.1564080715179443,
+      "learning_rate": 1.4385964912280704e-06,
+      "loss": 0.2834,
+      "mean_token_accuracy": 0.9084087669849396,
+      "num_tokens": 597950.0,
+      "step": 530
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 3.4902498722076416,
+      "learning_rate": 1.0877192982456142e-06,
+      "loss": 0.296,
+      "mean_token_accuracy": 0.904336941242218,
+      "num_tokens": 608908.0,
+      "step": 540
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 3.7762794494628906,
+      "learning_rate": 7.368421052631579e-07,
+      "loss": 0.2876,
+      "mean_token_accuracy": 0.9060073494911194,
+      "num_tokens": 619855.0,
+      "step": 550
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 3.163846969604492,
+      "learning_rate": 3.859649122807018e-07,
+      "loss": 0.2582,
+      "mean_token_accuracy": 0.9169736564159393,
+      "num_tokens": 631493.0,
+      "step": 560
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.375433921813965,
+      "learning_rate": 3.508771929824562e-08,
+      "loss": 0.2803,
+      "mean_token_accuracy": 0.911361163854599,
+      "num_tokens": 642210.0,
+      "step": 570
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 570,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.862484283808973e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-570/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffaee687bcf434da66f399553b6e3a647d1ffa26a027aa9caf4841c6cfe086c
+size 6161

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2377228dac033fa3ab97988d1c941a87c54a9374043c8325613c46dee547ab60
+size 4972454376

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df68711b51929151c16b6c14f2f1d02763922cdf8e51bfee69c54093ff45f450
+size 4832048608

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db975b3aa0e55a6469664a6ce4b4663c61ed6f8eca00eeece7ef835d72bc428d
+size 4832048656

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b824a72773ac74525a1d71004db221e1779ef5ee6e2f0f103385d986695043f
+size 4832048672

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c183a54b2f94bab76c992036ec9d20e8edfcd7752711f5ae889cc69f5f36ba
+size 3462482728

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 32762941440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffaee687bcf434da66f399553b6e3a647d1ffa26a027aa9caf4841c6cfe086c
+size 6161