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 +1,1540 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_module_list_cfg": [],
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "head_dim": 64,
+  "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,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_head_dim": 192,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "autoround_version": "0.8.0.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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.10.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.10.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.11.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.11.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.12.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.12.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.13.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.13.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.14.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.14.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.15.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.15.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.16.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.16.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.17.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.17.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.18.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.18.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.19.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.19.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.20.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.20.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.21.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.21.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.22.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.22.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.23.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.23.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.24.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.24.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.25.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.25.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.26.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.26.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.27.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.27.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.28.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.28.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.29.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.29.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.3.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.3.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.30.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.30.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.31.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.31.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.32.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.32.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.33.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.33.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.34.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.34.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.35.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.35.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.36.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.36.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.37.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.37.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.38.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.38.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.39.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.39.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.4.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.4.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.40.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.40.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.41.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.41.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.42.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.42.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.43.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.43.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.44.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.44.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.45.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.45.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.46.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.46.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.47.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.47.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.48.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.48.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.49.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.49.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.5.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.5.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.50.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.50.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.51.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.51.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.52.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.52.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.53.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.53.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.54.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.54.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.55.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.55.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.56.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.56.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.57.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.57.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.58.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.58.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.59.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.59.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.6.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.6.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.60.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.60.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.7.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.7.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.8.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.8.mlp.shared_experts.up_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.mlp.shared_experts.down_proj": {
+        "bits": 8
+      },
+      "model.layers.9.mlp.shared_experts.gate_proj": {
+        "bits": 8
+      },
+      "model.layers.9.mlp.shared_experts.up_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_interleave": true,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 40.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "transformers_version": "4.56.1",
+  "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": "4.56.1"
+}

model-00001-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703ef06b868c2d598dab11427aa7a00ecf6a99d49bffa25410cc2c5c90e292ca
+size 4995710664

model-00002-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc655ced1b36105733ed8b148aa2f4dd37fa6d921b94f9d154e332b3f824979
+size 4999591680

model-00003-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da42565e1aef66ac3265d4789587a2125a92341f083ef789267f580a68bee74f
+size 4995762096

model-00004-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5b07d9c2cd64fe4ba2f6985b1912ed9afc8faa8314058ce404b41c70a1e10c
+size 4999591192

model-00005-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142a194a48965b06b4ba5b2939e73ac510522950458d8d8a25e8a6c4e4034690
+size 4999591176

model-00006-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013aac65ba5a34aa916d0f35243062455a2cd97334a7a1a8bf00f570f1813486
+size 4999591384

model-00007-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee5edbf308abb53e16ef1c667c9fe30a149078292cd8dc1066e5071548ea67d
+size 4999591608

model-00008-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139cb00ce3d086a36a1aed2fc091a0de023072e9d2313ef780502c4511345cad
+size 4995762400

model-00009-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c81a75f64d7b4102eb1b76d3971c7685580bcf9aaee1ca7163a394f914f61c4
+size 4999591192

model-00010-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b32f2783bfc0cad2f37977c6ac41bac957d1e956721e002fce98226d68f26d9
+size 4999592560

model-00011-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91365a964adc6db75d592580510da52e75f61fcf8709631a09f09314cec7cac
+size 4999593080

model-00012-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac245373666959a07089b8a043332049588019e09440ad6f7e86f4c011892b5
+size 4999593480

model-00013-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7845cacea27c54f8e9f63ea02c57cb08a9b8dd04062d24b95ae7f82d88d81955
+size 4999593536

model-00014-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9991c5ffb98ed8de71fe4c2fef86912311a332bb1dc5f589d30496387f8c64
+size 4995764144

model-00015-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e078c0f9bca278d9baba37e14a0c3b33f336e8a9e1bc10602de0b97d0f09dea
+size 4999593096

model-00016-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c5c3733e761a0efa6632a6e98f9d9431c1b590b617d5acb7a92884783ecddc
+size 4999593080

model-00017-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3853be036896f2c72c83099ee9189d5a6f9401efeb99797c56b9256d3619341f
+size 4999593248

model-00018-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1b3e03d649d9783c9661588750ba72b98485bfd3430935da3c8608409a4b4e
+size 4999593512

model-00019-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe76912734a193a5150f16487bf86142302453eed321cbb9a63e588f87a4ec2b
+size 4995764408

model-00020-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712af5e0fd470826e8c2f9aae3d6150d23dc6355389a6123a7400ac8db2cab10
+size 4999593096

model-00021-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89d1673ac5a2b408e0fc387abd17b428a3154d27f04adb3e071d019b8870b97
+size 4999593080

model-00022-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1098bd43cc06f981f31e6b06e72aee9a25612669e6df03ce1ac426d878b55b28
+size 4999593080

model-00023-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c691792a6ce68b151874b91d93130a4b5320fa1e8cbf873bd397c3f7cb88ed9
+size 4999593440

model-00024-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09419e6a04c5d389fcb15cde7b2710e45a0b67b394b9311950c53ba8abd4447
+size 4999593512

model-00025-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0619c06e8fdd0e7dd8440fe34cfa2e98fa429b9a41b7d068b25bed2fb3d8b57c
+size 4995764216

model-00026-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c55e657b4a8464fa8df39711b614ecc3c0984b607172161156fd2062384e1
+size 4999593096

model-00027-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367ce952d1a57435332148a8eb41ed1671d152a6705366337f83ba5e3e799e73
+size 4999593080

model-00028-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d31fc80cd3f0aa58b0b491b3b43df641cdda8fabbeb99cf2f8e59ceef39b012
+size 4999593208

model-00029-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1224ef6ff84448c60fa4b9fe301250c15388b5c6cbfcb58d329ad332886b1a
+size 4999593512

model-00030-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a68fd7e0c834184057e08985a6ec3d74a238e4621697a6cedce7ade9f88302
+size 4999205472

model-00031-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47d4636cd955c53e7b97314f74145f34b925afc405af452ba5fb4c950455d74
+size 4996152080

model-00032-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8913646eb8d9913a6c5ad3c525409e7a488831e1a5219950ecd3765fbb6a7f1
+size 4999593080

model-00033-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684c02ae0841f49e40db1f3ae60c426cd49922c49524cdaa4d3e25556c9a8760
+size 4999593080

model-00034-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc18c532945bc84ba94e0a0c44d8394ce6a7fb6540511d83ad5842c6e9819bcb
+size 4999593400

model-00035-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c389187026d9ed6bcfc92a0fbf7cd02f355d73032e403718c62261022fb6c0da
+size 4999593512

model-00036-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf48b79855218765f8cf6e3bbf4be0e357ea076bba7b0f3e7cc7e85434b70f1
+size 4995764256

model-00037-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400161123244e49d1254d4ce168cf6fa2430200b34343f9f31b3485e097fd032
+size 4999593096

model-00038-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81366286a3b9a7f61bd1c80fc176fe3499113c2c42955c94e70d725b9435d854
+size 4999593080

model-00039-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a21429275f2cbfe668ba7e17241da12a85fc5a83edfa9da8a84ec7ff81e1abe
+size 4999593160

model-00040-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8240647013d396e134efd31c0e15e8fd6aa9a739af9f55b06d9bce95fdfb353
+size 4999593512

model-00041-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d57fcef5604a3e1657cf703eec11c7724424cf207b64027fc21e053ec61119
+size 4993807032

model-00042-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb63475587d22f8f0d5ec3faaad624f6428c0eba5f03dbb21bb916718d26f49
+size 4993923416

model-00043-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07929aa534df63c44db768d5ff3126e8a260d5e84a87bebac06cce62ebc26fe
+size 4999593096

model-00044-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30efdee55ca95b5325edc8b3b3ddd5f122ce25ec83126cc7e811324f426ef482
+size 4999593080

model-00045-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5a0619efb94ef12fed6a2439aa8f76779be45a3eab1e7378fdd37c8af0e478
+size 4999593360