Add files using upload-large-folder tool

.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 +1,1539 @@
+{
+  "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,
+  "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": "0.6.1.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.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",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.56.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

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 sha256:118c1bd57564a8cc357b54a83319a1268f6c0e022f4ce2cc8d3549aae56d9c99
+size 4995710664

model-00007-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6fdec602961dd94e355479c076aac7a72a4a535b730466b41e0cb591a7e347
+size 4999591608

model-00016-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41efc38b5b63773014829fc209a5be6cb2aeff3ea1b4d01d23d9ae1db1a2d7e1
+size 4999593080

model-00021-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174ccbd9b11842257b80f4da1fd94a8d9c631f18dd49f787447512b19f74f0dd
+size 4999593080

model-00040-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fb3ff28d4bb225af967e6cb1d005ebaad3148d8e0085f5b0d56bb15db5dd77
+size 4999593512

model-00041-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba562b08c01e3a4de0d392148a0712e442f05f15e3789334bf46412eb1f327a1
+size 4993807032

model-00043-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fccd19da91d67507c0f9f2c896759506f4899cf6703b6eb692c36227be35fa
+size 4999593096

model-00046-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ebc67ed08abfc78d5d71c172848690594e9179a4ea08b4b28d24631950d185
+size 4999593512

model-00050-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:952a7b122d544acecb6c01df90549f3e1c976ae5844f77ce6624b277381c360f
+size 4999593120

model-00062-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ec251eb5545d4fda94786cbd9c0165b825caa87b8c5c1aa23fd40669a02214
+size 4999593512

model-00071-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4daf567baa4ef965b996278fac08cf4228a164bb8805db03f5f19bbee5a4a485
+size 4999593080

model-00072-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3af9f0bffb442001896d73f95c2376af6e7e6784780fb986209654360268be
+size 4480112800

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e106ea7643cc5eea90a8e90c2f3e0e22637c40284469021bacf173beb32f11b
+size 12338633

quantization_config.json

@@ -0,0 +1,1476 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "iters": 0,
+  "autoround_version": "0.6.1.dev",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq",
+  "extra_config": {
+    "model.layers.0.self_attn.q_a_proj": {
+      "bits": 8
+    },
+    "model.layers.0.self_attn.q_b_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.mlp.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.0.mlp.up_proj": {
+      "bits": 8
+    },
+    "model.layers.0.mlp.down_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.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.mlp.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.1.mlp.up_proj": {
+      "bits": 8
+    },
+    "model.layers.1.mlp.down_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.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.mlp.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.2.mlp.up_proj": {
+      "bits": 8
+    },
+    "model.layers.2.mlp.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.3.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.3.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.4.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.4.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.5.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.5.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.6.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.6.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.7.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.7.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.8.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.8.mlp.shared_experts.down_proj": {
+      "bits": 8
+    },
+    "model.layers.9.self_attn.q_a_proj": {
+      "bits": 8
+    },
+    "model.layers.9.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.9.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.9.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.10.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.10.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.11.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.11.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.12.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.12.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.13.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.13.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.14.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.14.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.15.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.15.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.16.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.16.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.17.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.17.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.18.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.18.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.19.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.19.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.20.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.20.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.21.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.21.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.22.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.22.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.23.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.23.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.24.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.24.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.25.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.25.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.26.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.26.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.27.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.27.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.28.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.28.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.29.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.29.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.30.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.30.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.31.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.31.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.32.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.32.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.33.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.33.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.34.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.34.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.35.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.35.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.36.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.36.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.37.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.37.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.38.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.38.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.39.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.39.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.40.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.40.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.41.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.41.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.42.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.42.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.43.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.43.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.44.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.44.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.45.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.45.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.46.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.46.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.47.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.47.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.48.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.48.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.49.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.49.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.50.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.50.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.51.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.51.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.52.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.52.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.53.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.53.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.54.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.54.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.55.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.55.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.56.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.56.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.57.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.57.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.58.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.58.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.59.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.59.mlp.shared_experts.down_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.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.mlp.shared_experts.gate_proj": {
+      "bits": 8
+    },
+    "model.layers.60.mlp.shared_experts.up_proj": {
+      "bits": 8
+    },
+    "model.layers.60.mlp.shared_experts.down_proj": {
+      "bits": 8
+    }
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}