swiftkv llama 8b (#3)

- Add files using upload-large-folder tool (0043e1166d7b3ba799326ab3886a0600b60bcc17)

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/data-fast/llama-3.1-8b-instruct",
   "architectures": [
     "LlamaSwiftKVForCausalLM"
   ],
@@ -11,12 +10,13 @@
     128008,
     128009
   ],
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "key_value_group_size": 1,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama_swiftkv",
   "num_attention_heads": 32,
@@ -35,8 +35,8 @@
   "rope_theta": 500000.0,
   "swiftkv": true,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,10 +1,12 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
+  "do_sample": true,
   "eos_token_id": [
     128001,
     128008,
     128009
   ],
-  "transformers_version": "4.44.2"
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.53.0"
 }

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a37f6565cd20bbeb90033635d01222b672e6216c23f2e031b9b0c7feb9bcfca
+size 3986791344

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4d494587a3328773d6e3d9db66e2c88ea38d241db74c54c889172a45a70af4
+size 3926025416

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f067fb9f93a7e49cfc1dd5df92f5af5daa9d22699c63f309291d1f9659845b44
+size 3892456600

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a876efb015ecd601f5a1cb7b528fff60456bc073b80791083258f6c2467c2a
+size 3892456600

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f41521fe7a994bc50ae806683ac5638d507168f51847dfbd90abd6da5e60cd
+size 1168147104

model.safetensors.index.json

@@ -1,347 +1,348 @@
 {
   "metadata": {
-    "total_size": 33731674112
+    "total_parameters": 8432918528,
+    "total_size": 16865837056
   },
   "weight_map": {
-    "lm_head.weight": "model-00009-of-00009.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.k_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.q_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.v_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.k_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.q_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.v_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.k_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.q_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.v_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.k_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.q_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.v_proj_swiftkv.weight": "model-00005-of-00009.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.self_attn.k_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.self_attn.q_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.20.self_attn.v_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.k_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.q_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.v_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.k_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.q_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.v_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.k_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.q_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.v_proj_swiftkv.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.self_attn.k_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.self_attn.q_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.24.self_attn.v_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.self_attn.k_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.self_attn.q_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.25.self_attn.v_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.k_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.q_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.v_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.k_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.q_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.v_proj_swiftkv.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.self_attn.k_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.self_attn.q_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.28.self_attn.v_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.self_attn.k_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.self_attn.q_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.29.self_attn.v_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.self_attn.k_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.self_attn.q_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.30.self_attn.v_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00009-of-00009.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.self_attn.k_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.self_attn.q_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.self_attn.v_proj_swiftkv.weight": "model-00008-of-00009.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.norm.weight": "model-00009-of-00009.safetensors",
-    "model.norm_swiftkv.weight": "model-00009-of-00009.safetensors"
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj_swiftkv.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj_swiftkv.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors",
+    "model.norm_swiftkv.weight": "model-00005-of-00005.safetensors"
   }
 }

tokenizer_config.json

@@ -2050,9 +2050,9 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"