Upload folder using huggingface_hub

.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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,3 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if not thinking is defined %}{% set thinking = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
+
+' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- if ns.is_last_user %}{{'<｜Assistant｜></think>'}}{%- endif %}{%- set ns.is_last_user = false -%}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- else %}{{message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'<｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}{%- if ns.is_last_user %}{{'<｜Assistant｜>'}}{%- if message['prefix'] is defined and message['prefix'] and thinking %}{{'<think>'}}  {%- else %}{{'</think>'}}{%- endif %}{%- endif %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{%- set content = message['content'] -%}{%- if '</think>' in content %}{%- set content = content.split('</think>', 1)[1] -%}{%- endif %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{{'<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endfor -%}{%- if add_generation_prompt and ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{%- if not thinking %}{{'</think>'}}{%- else %}{{'<think>'}}{%- endif %}{% endif %}

config.json

@@ -0,0 +1,1014 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 2,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "autoround_version": "0.6.1.dev",
+    "bits": 4,
+    "data_type": "int",
+    "extra_config": {
+      "model.layers.0.mlp.down_proj": {
+        "bits": 8
+      },
+      "model.layers.0.mlp.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.0.mlp.up_proj": {
+        "bits": 8
+      },
+      "model.layers.0.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.0.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.0.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.0.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.0.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.1.mlp.down_proj": {
+        "bits": 8
+      },
+      "model.layers.1.mlp.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.1.mlp.up_proj": {
+        "bits": 8
+      },
+      "model.layers.1.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.1.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.1.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.1.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.1.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.10.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.10.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.10.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.10.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.10.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.11.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.11.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.11.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.11.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.11.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.12.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.12.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.12.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.12.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.12.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.13.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.13.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.13.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.13.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.13.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.14.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.14.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.14.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.14.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.14.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.15.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.15.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.15.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.15.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.15.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.16.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.16.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.16.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.16.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.16.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.17.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.17.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.17.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.17.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.17.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.18.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.18.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.18.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.18.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.18.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.19.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.19.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.19.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.19.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.19.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.2.mlp.down_proj": {
+        "bits": 8
+      },
+      "model.layers.2.mlp.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.2.mlp.up_proj": {
+        "bits": 8
+      },
+      "model.layers.2.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.2.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.2.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.2.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.2.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.20.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.20.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.20.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.20.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.20.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.21.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.21.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.21.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.21.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.21.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.22.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.22.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.22.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.22.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.22.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.23.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.23.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.23.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.23.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.23.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.24.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.24.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.24.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.24.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.24.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.25.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.25.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.25.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.25.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.25.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.26.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.26.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.26.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.26.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.26.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.27.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.27.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.27.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.27.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.27.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.28.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.28.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.28.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.28.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.28.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.29.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.29.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.29.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.29.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.29.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.3.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.3.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.3.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.3.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.3.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.30.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.30.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.30.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.30.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.30.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.31.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.31.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.31.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.31.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.31.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.32.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.32.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.32.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.32.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.32.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.33.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.33.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.33.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.33.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.33.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.34.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.34.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.34.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.34.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.34.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.35.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.35.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.35.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.35.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.35.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.36.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.36.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.36.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.36.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.36.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.37.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.37.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.37.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.37.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.37.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.38.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.38.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.38.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.38.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.38.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.39.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.39.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.39.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.39.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.39.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.4.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.4.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.4.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.4.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.4.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.40.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.40.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.40.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.40.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.40.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.41.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.41.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.41.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.41.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.41.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.42.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.42.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.42.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.42.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.42.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.43.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.43.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.43.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.43.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.43.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.44.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.44.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.44.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.44.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.44.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.45.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.45.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.45.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.45.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.45.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.46.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.46.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.46.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.46.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.46.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.47.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.47.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.47.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.47.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.47.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.48.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.48.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.48.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.48.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.48.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.49.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.49.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.49.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.49.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.49.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.5.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.5.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.5.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.5.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.5.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.50.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.50.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.50.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.50.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.50.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.51.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.51.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.51.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.51.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.51.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.52.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.52.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.52.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.52.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.52.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.53.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.53.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.53.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.53.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.53.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.54.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.54.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.54.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.54.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.54.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.55.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.55.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.55.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.55.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.55.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.56.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.56.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.56.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.56.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.56.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.57.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.57.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.57.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.57.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.57.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.58.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.58.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.58.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.58.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.58.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.59.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.59.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.59.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.59.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.59.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.6.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.6.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.6.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.6.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.6.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.60.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.60.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.60.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.60.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.60.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.7.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.7.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.7.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.7.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.7.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.8.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.8.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.8.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.8.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.8.self_attn.q_b_proj": {
+        "bits": 8
+      },
+      "model.layers.9.self_attn.kv_a_proj_with_mqa": {
+        "bits": 8
+      },
+      "model.layers.9.self_attn.kv_b_proj": {
+        "bits": 8
+      },
+      "model.layers.9.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.layers.9.self_attn.q_a_proj": {
+        "bits": 8
+      },
+      "model.layers.9.self_attn.q_b_proj": {
+        "bits": 8
+      }
+    },
+    "group_size": 128,
+    "iters": 0,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.56.0.dev0",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,199 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.56.0.dev0"
+}

model-00001-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca84f9f40ef334eef962405e9688404ae652eb85eef733e7dfe9fd7d8e40dc6d
+size 4995710664

model-00002-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a5ba61ae9bf2b3907e48105177902846e063f40a76301c19907c68f47c95b1
+size 5000051392

model-00003-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08a3f557e84a92e41f1e92f99f550cc0d8a8442f21b95eb3fa480703eecc1f8
+size 4995991608

model-00004-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7020b0c09d1aca0b1a508d4d3039b3904dbd74953334cd8a2769ec3608b9108b
+size 5000050912

model-00005-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f624ca05d3b54dfc34267ee659ba12d15d5b372db2feec13fe2b496a2d8211
+size 5000222944

model-00006-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a0f1fb2164bab6a13fa7a54501d09996c34d7e41a6cb2d39d9d621e0410ad4
+size 4992940416

model-00007-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4be835f87031118ce99f89b55553273a1956f44fb987f632e5bdc7374688407
+size 5000051336

model-00008-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68acaf80fe8ed102b0a1f946c9fc49548de37d408c89460d8fd3a49d98f49dd
+size 4995991936

model-00009-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347da340973bc3c9e78814c9b0b37007d2342092961b2260ecb8360db190d912
+size 5000050912

model-00010-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f808ce67c8deee35f928cd4f507d0b7d91b9782752adce381940569cb390982f
+size 5000224376

model-00011-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c32b02f7fc2fbaa588c4a1a561c3c845b5cdcc97e4f9d4d990558d3db30414
+size 4992942152

model-00012-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9112c487f3ecf185605d4cf4dac92138519dbe5ace64f3a9be1c9a04630eea4b
+size 5000053152

model-00013-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c184fc0ee3bf5e33047f40f4c2855844c909040a4b95b2cff34bc99b018ff625
+size 5000225280

model-00014-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9909ab2a8a7ce7bc5a7c5b19feeb2d9f3e060c4d0ca8179c58db9a738be83436
+size 4996051216

model-00015-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da31552606f00a3a21049637416f845c0f55cedc40e060f120114447503cf0d3
+size 5000052816

model-00016-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0bc3bad1cac7808d24cd57b4cb3409052a9b06de766d9413fea2f8c868b6600
+size 5000224856

model-00017-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b5c9c247567c7624beea886458abeae76c9958aacf888925f01879dd5ac209
+size 4992942208

model-00018-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c04f2c0095391732d42259480fda5d2219e457d01e0179e36e450ca078f4db3
+size 5000053248

model-00019-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7aba70afcdf3ce089821a36d63c5dbfec323c4bac17c8354057770ecb9a11e3
+size 4887946080

model-00020-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a936066825e6e83310f5beda543af76caa7454c228261ccb6ebcecb388b5d9
+size 4993923416

model-00021-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf954fdfee1482d82ae4b7dd3b81f3c96e94503c3cd0b879cd84d8601f39e6b
+size 5000052816

model-00022-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e391cdccc84a5b3ec1723c5f871e2070a0d521ff77c356bf36ae76f6878b03
+size 5000224856

model-00023-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702015a7919d71819afb95f0c9e3cf74216fcf4596f9062189e73fcf569f9d39
+size 4992942408

model-00024-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422dd7e4209744716eeaa76779f30457b7d1b2e6bf105d4947e671ce6921e523
+size 5000053248

model-00025-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476c13bc42d1fffcabcf1f83229aa435201c5a2f92e008305e3278d674fa792e
+size 4995993824

model-00026-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441cf0656c2358e3e15a326b8f280de0ae09a4b7481e0752d85571a6e7ad76c1
+size 5000052816

model-00027-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0eaca5ef29ed2e0b985af88687d13699f075332e45f006c66530e0c740985c
+size 5000224856

model-00028-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db427a1585b57fdd8fc3b84138c00548c9b310e0d5fb2fe3f69944eae6dc5d0
+size 4992942152

model-00029-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e276ebe719c214518a53b38396ad526159d32071d8df3fbd99316e9add87be57
+size 5000053232

model-00030-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ae27cc538f8ab8da4ce267c76d7b0f4dc33bccaf5067a0b12ba5cf143a2e31
+size 5000225304

model-00031-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983b30e8172ebda2b844d5287959e8c50d731fa3371a207257d680aa5b9121cb
+size 4996051112

model-00032-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee2587fcdbcb7966e2e46e557b9a86df222f86fc9ff3c78a37b08b45c1134b5
+size 5000052816

model-00033-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d88968cec7322b8b0559f518f0d2b3fab1adbbe1940a3e0078fdb810f4a040
+size 5000224856

model-00034-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f2715617fe58702606a3891d3eff57ce5f6b402cbeeefacea858a64b3f0b01
+size 4992942288

model-00035-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa403dc7a766d421d56db4fab0e8144c33307cbface657e58ce08dd0723a21d7
+size 5000053248

model-00036-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af20d5f58e03c46ebcb02a9127eb3a80cd96257e778c7000b2a28a609c1864f
+size 4999664696

model-00037-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74459e2953f3b36afa8426eab858336930b597ac3c652bb16e30ba4fb2f301db
+size 4996611560

model-00038-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d06df18ed937935a1fbafb1d212ac8c0c5225f2a32285f8f364092586c45f5
+size 5000052816

model-00039-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de186711e1ef31eea8eb178c4cb45f39130d77623617982726c2f73ec384667
+size 5000224856

model-00040-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ab209db638b7e349a3f8266abed57b7bcb84320b4e33aff59e8e2aff184f5b
+size 4992942440

model-00041-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52b41a366e94ca5c038940517cd4f594850c5bcc2cc65f27686e267e99b7675
+size 5000053248

model-00042-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f148561dd6769a5ff5c8242aaea132cbe7c13031dc6af0f5b7a72bb5800d2a
+size 4995993792

model-00043-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06564b3422d93e8d8a171ab270de1baff4e4aca1d997b06a496079b1078f78c
+size 5000052816

model-00044-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9c0c8c6a4aef00b34a1b2766ae347ab853629c7da6f9c48e942c65a55c381c
+size 5000224856

model-00045-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4b7abd0c88a285639dcefe4ed905d0d0b31958c94ea3353df623737a0e3f27
+size 4992942176