Add files using upload-large-folder tool

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

4bit-asym_8bit-sym/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/README.md

@@ -0,0 +1,18 @@
+# Quantized Model Checkpoint
+
+**Base model:** Qwen/Qwen3-8B
+
+**Average bitwidth:** 6.9579
+
+**Sensitivity method:** shapley
+
+**Constraints:**
+- max_kl: 0.01
+- min_eap: 0.985
+
+**Metrics:**
+- final_kl: 0.003765
+- final_eap: 0.985113
+- final_etl: 0.014887
+
+See `quantization_config.txt` for full configuration details.

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/added_tokens.json

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/chat_template.jinja

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/quantization_config.txt

@@ -0,0 +1,460 @@
+# Model: Qwen/Qwen3-8B
+# Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4bit_asym_8bit_sym_g128/Qwen3-8B
+# Sensitivity method: shapley
+# Estimation method: permutation
+# Available bitwidths: [4, 8]
+# Bitwidth map: {4: 4.156, 5: 5.156, 6: 6.156, 7: 7.156, 8: 8.156}
+#
+# Layer groups: 144 groups (fused layers share bitwidth)
+#   block_0:mlp.gate_proj,mlp.up_proj.block_0:mlp.gate_proj,mlp.up_proj: group 0, 2 layers
+#   block_0:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 1, 3 layers
+#   block_10:mlp.gate_proj,mlp.up_proj.block_10:mlp.gate_proj,mlp.up_proj: group 20, 2 layers
+#   block_10:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 21, 3 layers
+#   block_11:mlp.gate_proj,mlp.up_proj.block_11:mlp.gate_proj,mlp.up_proj: group 22, 2 layers
+#   block_11:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 23, 3 layers
+#   block_12:mlp.gate_proj,mlp.up_proj.block_12:mlp.gate_proj,mlp.up_proj: group 24, 2 layers
+#   block_12:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 25, 3 layers
+#   block_13:mlp.gate_proj,mlp.up_proj.block_13:mlp.gate_proj,mlp.up_proj: group 26, 2 layers
+#   block_13:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 27, 3 layers
+#   block_14:mlp.gate_proj,mlp.up_proj.block_14:mlp.gate_proj,mlp.up_proj: group 28, 2 layers
+#   block_14:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 29, 3 layers
+#   block_15:mlp.gate_proj,mlp.up_proj.block_15:mlp.gate_proj,mlp.up_proj: group 30, 2 layers
+#   block_15:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 31, 3 layers
+#   block_16:mlp.gate_proj,mlp.up_proj.block_16:mlp.gate_proj,mlp.up_proj: group 32, 2 layers
+#   block_16:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 33, 3 layers
+#   block_17:mlp.gate_proj,mlp.up_proj.block_17:mlp.gate_proj,mlp.up_proj: group 34, 2 layers
+#   block_17:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 35, 3 layers
+#   block_18:mlp.gate_proj,mlp.up_proj.block_18:mlp.gate_proj,mlp.up_proj: group 36, 2 layers
+#   block_18:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 37, 3 layers
+#   block_19:mlp.gate_proj,mlp.up_proj.block_19:mlp.gate_proj,mlp.up_proj: group 38, 2 layers
+#   block_19:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 39, 3 layers
+#   block_1:mlp.gate_proj,mlp.up_proj.block_1:mlp.gate_proj,mlp.up_proj: group 2, 2 layers
+#   block_1:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 3, 3 layers
+#   block_20:mlp.gate_proj,mlp.up_proj.block_20:mlp.gate_proj,mlp.up_proj: group 40, 2 layers
+#   block_20:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 41, 3 layers
+#   block_21:mlp.gate_proj,mlp.up_proj.block_21:mlp.gate_proj,mlp.up_proj: group 42, 2 layers
+#   block_21:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 43, 3 layers
+#   block_22:mlp.gate_proj,mlp.up_proj.block_22:mlp.gate_proj,mlp.up_proj: group 44, 2 layers
+#   block_22:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 45, 3 layers
+#   block_23:mlp.gate_proj,mlp.up_proj.block_23:mlp.gate_proj,mlp.up_proj: group 46, 2 layers
+#   block_23:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 47, 3 layers
+#   block_24:mlp.gate_proj,mlp.up_proj.block_24:mlp.gate_proj,mlp.up_proj: group 48, 2 layers
+#   block_24:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 49, 3 layers
+#   block_25:mlp.gate_proj,mlp.up_proj.block_25:mlp.gate_proj,mlp.up_proj: group 50, 2 layers
+#   block_25:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 51, 3 layers
+#   block_26:mlp.gate_proj,mlp.up_proj.block_26:mlp.gate_proj,mlp.up_proj: group 52, 2 layers
+#   block_26:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 53, 3 layers
+#   block_27:mlp.gate_proj,mlp.up_proj.block_27:mlp.gate_proj,mlp.up_proj: group 54, 2 layers
+#   block_27:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 55, 3 layers
+#   block_28:mlp.gate_proj,mlp.up_proj.block_28:mlp.gate_proj,mlp.up_proj: group 56, 2 layers
+#   block_28:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 57, 3 layers
+#   block_29:mlp.gate_proj,mlp.up_proj.block_29:mlp.gate_proj,mlp.up_proj: group 58, 2 layers
+#   block_29:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 59, 3 layers
+#   block_2:mlp.gate_proj,mlp.up_proj.block_2:mlp.gate_proj,mlp.up_proj: group 4, 2 layers
+#   block_2:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 5, 3 layers
+#   block_30:mlp.gate_proj,mlp.up_proj.block_30:mlp.gate_proj,mlp.up_proj: group 60, 2 layers
+#   block_30:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 61, 3 layers
+#   block_31:mlp.gate_proj,mlp.up_proj.block_31:mlp.gate_proj,mlp.up_proj: group 62, 2 layers
+#   block_31:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 63, 3 layers
+#   block_32:mlp.gate_proj,mlp.up_proj.block_32:mlp.gate_proj,mlp.up_proj: group 64, 2 layers
+#   block_32:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 65, 3 layers
+#   block_33:mlp.gate_proj,mlp.up_proj.block_33:mlp.gate_proj,mlp.up_proj: group 66, 2 layers
+#   block_33:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 67, 3 layers
+#   block_34:mlp.gate_proj,mlp.up_proj.block_34:mlp.gate_proj,mlp.up_proj: group 68, 2 layers
+#   block_34:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 69, 3 layers
+#   block_35:mlp.gate_proj,mlp.up_proj.block_35:mlp.gate_proj,mlp.up_proj: group 70, 2 layers
+#   block_35:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 71, 3 layers
+#   block_3:mlp.gate_proj,mlp.up_proj.block_3:mlp.gate_proj,mlp.up_proj: group 6, 2 layers
+#   block_3:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 7, 3 layers
+#   block_4:mlp.gate_proj,mlp.up_proj.block_4:mlp.gate_proj,mlp.up_proj: group 8, 2 layers
+#   block_4:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 9, 3 layers
+#   block_5:mlp.gate_proj,mlp.up_proj.block_5:mlp.gate_proj,mlp.up_proj: group 10, 2 layers
+#   block_5:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 11, 3 layers
+#   block_6:mlp.gate_proj,mlp.up_proj.block_6:mlp.gate_proj,mlp.up_proj: group 12, 2 layers
+#   block_6:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 13, 3 layers
+#   block_7:mlp.gate_proj,mlp.up_proj.block_7:mlp.gate_proj,mlp.up_proj: group 14, 2 layers
+#   block_7:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 15, 3 layers
+#   block_8:mlp.gate_proj,mlp.up_proj.block_8:mlp.gate_proj,mlp.up_proj: group 16, 2 layers
+#   block_8:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 17, 3 layers
+#   block_9:mlp.gate_proj,mlp.up_proj.block_9:mlp.gate_proj,mlp.up_proj: group 18, 2 layers
+#   block_9:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 19, 3 layers
+#   Fused in model.layers.0:
+#     - self_attn.o_proj (group 84, 1 layers)
+#     - mlp.down_proj (group 88, 1 layers)
+#   Fused in model.layers.1:
+#     - mlp.down_proj (group 72, 1 layers)
+#     - self_attn.o_proj (group 94, 1 layers)
+#   Fused in model.layers.10:
+#     - self_attn.o_proj (group 85, 1 layers)
+#     - mlp.down_proj (group 87, 1 layers)
+#   Fused in model.layers.11:
+#     - self_attn.o_proj (group 89, 1 layers)
+#     - mlp.down_proj (group 90, 1 layers)
+#   Fused in model.layers.12:
+#     - self_attn.o_proj (group 91, 1 layers)
+#     - mlp.down_proj (group 92, 1 layers)
+#   Fused in model.layers.13:
+#     - self_attn.o_proj (group 74, 1 layers)
+#     - mlp.down_proj (group 124, 1 layers)
+#   Fused in model.layers.14:
+#     - mlp.down_proj (group 112, 1 layers)
+#     - self_attn.o_proj (group 125, 1 layers)
+#   Fused in model.layers.15:
+#     - mlp.down_proj (group 110, 1 layers)
+#     - self_attn.o_proj (group 119, 1 layers)
+#   Fused in model.layers.16:
+#     - self_attn.o_proj (group 104, 1 layers)
+#     - mlp.down_proj (group 120, 1 layers)
+#   Fused in model.layers.17:
+#     - self_attn.o_proj (group 132, 1 layers)
+#     - mlp.down_proj (group 133, 1 layers)
+#   Fused in model.layers.18:
+#     - self_attn.o_proj (group 100, 1 layers)
+#     - mlp.down_proj (group 128, 1 layers)
+#   Fused in model.layers.19:
+#     - self_attn.o_proj (group 102, 1 layers)
+#     - mlp.down_proj (group 121, 1 layers)
+#   Fused in model.layers.2:
+#     - mlp.down_proj (group 75, 1 layers)
+#     - self_attn.o_proj (group 86, 1 layers)
+#   Fused in model.layers.20:
+#     - self_attn.o_proj (group 111, 1 layers)
+#     - mlp.down_proj (group 123, 1 layers)
+#   Fused in model.layers.21:
+#     - self_attn.o_proj (group 103, 1 layers)
+#     - mlp.down_proj (group 105, 1 layers)
+#   Fused in model.layers.22:
+#     - mlp.down_proj (group 106, 1 layers)
+#     - self_attn.o_proj (group 134, 1 layers)
+#   Fused in model.layers.23:
+#     - mlp.down_proj (group 109, 1 layers)
+#     - self_attn.o_proj (group 129, 1 layers)
+#   Fused in model.layers.24:
+#     - self_attn.o_proj (group 127, 1 layers)
+#     - mlp.down_proj (group 135, 1 layers)
+#   Fused in model.layers.25:
+#     - self_attn.o_proj (group 99, 1 layers)
+#     - mlp.down_proj (group 138, 1 layers)
+#   Fused in model.layers.26:
+#     - self_attn.o_proj (group 117, 1 layers)
+#     - mlp.down_proj (group 130, 1 layers)
+#   Fused in model.layers.27:
+#     - self_attn.o_proj (group 131, 1 layers)
+#     - mlp.down_proj (group 136, 1 layers)
+#   Fused in model.layers.28:
+#     - mlp.down_proj (group 101, 1 layers)
+#     - self_attn.o_proj (group 107, 1 layers)
+#   Fused in model.layers.29:
+#     - mlp.down_proj (group 118, 1 layers)
+#     - self_attn.o_proj (group 140, 1 layers)
+#   Fused in model.layers.3:
+#     - self_attn.o_proj (group 81, 1 layers)
+#     - mlp.down_proj (group 96, 1 layers)
+#   Fused in model.layers.30:
+#     - self_attn.o_proj (group 113, 1 layers)
+#     - mlp.down_proj (group 114, 1 layers)
+#   Fused in model.layers.31:
+#     - self_attn.o_proj (group 126, 1 layers)
+#     - mlp.down_proj (group 137, 1 layers)
+#   Fused in model.layers.32:
+#     - self_attn.o_proj (group 139, 1 layers)
+#     - mlp.down_proj (group 141, 1 layers)
+#   Fused in model.layers.33:
+#     - self_attn.o_proj (group 115, 1 layers)
+#     - mlp.down_proj (group 116, 1 layers)
+#   Fused in model.layers.34:
+#     - mlp.down_proj (group 122, 1 layers)
+#     - self_attn.o_proj (group 143, 1 layers)
+#   Fused in model.layers.35:
+#     - mlp.down_proj (group 108, 1 layers)
+#     - self_attn.o_proj (group 142, 1 layers)
+#   Fused in model.layers.4:
+#     - self_attn.o_proj (group 79, 1 layers)
+#     - mlp.down_proj (group 82, 1 layers)
+#   Fused in model.layers.5:
+#     - self_attn.o_proj (group 78, 1 layers)
+#     - mlp.down_proj (group 80, 1 layers)
+#   Fused in model.layers.6:
+#     - self_attn.o_proj (group 76, 1 layers)
+#     - mlp.down_proj (group 98, 1 layers)
+#   Fused in model.layers.7:
+#     - self_attn.o_proj (group 93, 1 layers)
+#     - mlp.down_proj (group 97, 1 layers)
+#   Fused in model.layers.8:
+#     - mlp.down_proj (group 73, 1 layers)
+#     - self_attn.o_proj (group 83, 1 layers)
+#   Fused in model.layers.9:
+#     - mlp.down_proj (group 77, 1 layers)
+#     - self_attn.o_proj (group 95, 1 layers)
+#
+# Mode: binary_search_constraint (measured)
+# Constraint max_kl: 0.01
+# Constraint min_eap: 0.985
+# Weights: nll=0.0, kl=0.0, eap=1.0
+#
+# Average bitwidth: 6.9579
+# Total params: 6945767424
+# Total bits: 48328179974
+# Final KL: 0.003765
+# Final EAP: 0.985113
+# Final ETL: 0.014887
+# Satisfies constraints: True
+# Solver calls: 9
+# Evaluations: 9
+#
+# Bitwidth distribution:
+#   8-bit: 210 layers (83.3%)
+#   4-bit: 42 layers (16.7%)
+#
+model.layers.0.mlp.gate_proj: 4
+model.layers.0.mlp.up_proj: 4
+model.layers.0.self_attn.k_proj: 8
+model.layers.0.self_attn.q_proj: 8
+model.layers.0.self_attn.v_proj: 8
+model.layers.1.mlp.gate_proj: 4
+model.layers.1.mlp.up_proj: 4
+model.layers.1.self_attn.k_proj: 8
+model.layers.1.self_attn.q_proj: 8
+model.layers.1.self_attn.v_proj: 8
+model.layers.2.mlp.gate_proj: 4
+model.layers.2.mlp.up_proj: 4
+model.layers.2.self_attn.k_proj: 8
+model.layers.2.self_attn.q_proj: 8
+model.layers.2.self_attn.v_proj: 8
+model.layers.3.mlp.gate_proj: 4
+model.layers.3.mlp.up_proj: 4
+model.layers.3.self_attn.k_proj: 8
+model.layers.3.self_attn.q_proj: 8
+model.layers.3.self_attn.v_proj: 8
+model.layers.4.mlp.gate_proj: 4
+model.layers.4.mlp.up_proj: 4
+model.layers.4.self_attn.k_proj: 8
+model.layers.4.self_attn.q_proj: 8
+model.layers.4.self_attn.v_proj: 8
+model.layers.5.mlp.gate_proj: 4
+model.layers.5.mlp.up_proj: 4
+model.layers.5.self_attn.k_proj: 8
+model.layers.5.self_attn.q_proj: 8
+model.layers.5.self_attn.v_proj: 8
+model.layers.6.mlp.gate_proj: 8
+model.layers.6.mlp.up_proj: 8
+model.layers.6.self_attn.k_proj: 8
+model.layers.6.self_attn.q_proj: 8
+model.layers.6.self_attn.v_proj: 8
+model.layers.7.mlp.gate_proj: 8
+model.layers.7.mlp.up_proj: 8
+model.layers.7.self_attn.k_proj: 8
+model.layers.7.self_attn.q_proj: 8
+model.layers.7.self_attn.v_proj: 8
+model.layers.8.mlp.gate_proj: 8
+model.layers.8.mlp.up_proj: 8
+model.layers.8.self_attn.k_proj: 8
+model.layers.8.self_attn.q_proj: 8
+model.layers.8.self_attn.v_proj: 8
+model.layers.9.mlp.gate_proj: 8
+model.layers.9.mlp.up_proj: 8
+model.layers.9.self_attn.k_proj: 8
+model.layers.9.self_attn.q_proj: 8
+model.layers.9.self_attn.v_proj: 8
+model.layers.10.mlp.gate_proj: 8
+model.layers.10.mlp.up_proj: 8
+model.layers.10.self_attn.k_proj: 8
+model.layers.10.self_attn.q_proj: 8
+model.layers.10.self_attn.v_proj: 8
+model.layers.11.mlp.gate_proj: 8
+model.layers.11.mlp.up_proj: 8
+model.layers.11.self_attn.k_proj: 8
+model.layers.11.self_attn.q_proj: 8
+model.layers.11.self_attn.v_proj: 8
+model.layers.12.mlp.gate_proj: 8
+model.layers.12.mlp.up_proj: 8
+model.layers.12.self_attn.k_proj: 8
+model.layers.12.self_attn.q_proj: 8
+model.layers.12.self_attn.v_proj: 8
+model.layers.13.mlp.gate_proj: 8
+model.layers.13.mlp.up_proj: 8
+model.layers.13.self_attn.k_proj: 8
+model.layers.13.self_attn.q_proj: 8
+model.layers.13.self_attn.v_proj: 8
+model.layers.14.mlp.gate_proj: 8
+model.layers.14.mlp.up_proj: 8
+model.layers.14.self_attn.k_proj: 8
+model.layers.14.self_attn.q_proj: 8
+model.layers.14.self_attn.v_proj: 8
+model.layers.15.mlp.gate_proj: 8
+model.layers.15.mlp.up_proj: 8
+model.layers.15.self_attn.k_proj: 8
+model.layers.15.self_attn.q_proj: 8
+model.layers.15.self_attn.v_proj: 8
+model.layers.16.mlp.gate_proj: 8
+model.layers.16.mlp.up_proj: 8
+model.layers.16.self_attn.k_proj: 8
+model.layers.16.self_attn.q_proj: 8
+model.layers.16.self_attn.v_proj: 8
+model.layers.17.mlp.gate_proj: 8
+model.layers.17.mlp.up_proj: 8
+model.layers.17.self_attn.k_proj: 8
+model.layers.17.self_attn.q_proj: 8
+model.layers.17.self_attn.v_proj: 8
+model.layers.18.mlp.gate_proj: 8
+model.layers.18.mlp.up_proj: 8
+model.layers.18.self_attn.k_proj: 8
+model.layers.18.self_attn.q_proj: 8
+model.layers.18.self_attn.v_proj: 8
+model.layers.19.mlp.gate_proj: 8
+model.layers.19.mlp.up_proj: 8
+model.layers.19.self_attn.k_proj: 8
+model.layers.19.self_attn.q_proj: 8
+model.layers.19.self_attn.v_proj: 8
+model.layers.20.mlp.gate_proj: 4
+model.layers.20.mlp.up_proj: 4
+model.layers.20.self_attn.k_proj: 8
+model.layers.20.self_attn.q_proj: 8
+model.layers.20.self_attn.v_proj: 8
+model.layers.21.mlp.gate_proj: 8
+model.layers.21.mlp.up_proj: 8
+model.layers.21.self_attn.k_proj: 8
+model.layers.21.self_attn.q_proj: 8
+model.layers.21.self_attn.v_proj: 8
+model.layers.22.mlp.gate_proj: 8
+model.layers.22.mlp.up_proj: 8
+model.layers.22.self_attn.k_proj: 8
+model.layers.22.self_attn.q_proj: 8
+model.layers.22.self_attn.v_proj: 8
+model.layers.23.mlp.gate_proj: 4
+model.layers.23.mlp.up_proj: 4
+model.layers.23.self_attn.k_proj: 8
+model.layers.23.self_attn.q_proj: 8
+model.layers.23.self_attn.v_proj: 8
+model.layers.24.mlp.gate_proj: 8
+model.layers.24.mlp.up_proj: 8
+model.layers.24.self_attn.k_proj: 8
+model.layers.24.self_attn.q_proj: 8
+model.layers.24.self_attn.v_proj: 8
+model.layers.25.mlp.gate_proj: 4
+model.layers.25.mlp.up_proj: 4
+model.layers.25.self_attn.k_proj: 8
+model.layers.25.self_attn.q_proj: 8
+model.layers.25.self_attn.v_proj: 8
+model.layers.26.mlp.gate_proj: 4
+model.layers.26.mlp.up_proj: 4
+model.layers.26.self_attn.k_proj: 8
+model.layers.26.self_attn.q_proj: 8
+model.layers.26.self_attn.v_proj: 8
+model.layers.27.mlp.gate_proj: 8
+model.layers.27.mlp.up_proj: 8
+model.layers.27.self_attn.k_proj: 8
+model.layers.27.self_attn.q_proj: 8
+model.layers.27.self_attn.v_proj: 8
+model.layers.28.mlp.gate_proj: 8
+model.layers.28.mlp.up_proj: 8
+model.layers.28.self_attn.k_proj: 8
+model.layers.28.self_attn.q_proj: 8
+model.layers.28.self_attn.v_proj: 8
+model.layers.29.mlp.gate_proj: 8
+model.layers.29.mlp.up_proj: 8
+model.layers.29.self_attn.k_proj: 8
+model.layers.29.self_attn.q_proj: 8
+model.layers.29.self_attn.v_proj: 8
+model.layers.30.mlp.gate_proj: 8
+model.layers.30.mlp.up_proj: 8
+model.layers.30.self_attn.k_proj: 8
+model.layers.30.self_attn.q_proj: 8
+model.layers.30.self_attn.v_proj: 8
+model.layers.31.mlp.gate_proj: 8
+model.layers.31.mlp.up_proj: 8
+model.layers.31.self_attn.k_proj: 8
+model.layers.31.self_attn.q_proj: 8
+model.layers.31.self_attn.v_proj: 8
+model.layers.32.mlp.gate_proj: 8
+model.layers.32.mlp.up_proj: 8
+model.layers.32.self_attn.k_proj: 8
+model.layers.32.self_attn.q_proj: 8
+model.layers.32.self_attn.v_proj: 8
+model.layers.33.mlp.gate_proj: 8
+model.layers.33.mlp.up_proj: 8
+model.layers.33.self_attn.k_proj: 8
+model.layers.33.self_attn.q_proj: 8
+model.layers.33.self_attn.v_proj: 8
+model.layers.34.mlp.gate_proj: 8
+model.layers.34.mlp.up_proj: 8
+model.layers.34.self_attn.k_proj: 8
+model.layers.34.self_attn.q_proj: 8
+model.layers.34.self_attn.v_proj: 8
+model.layers.35.mlp.gate_proj: 8
+model.layers.35.mlp.up_proj: 8
+model.layers.35.self_attn.k_proj: 8
+model.layers.35.self_attn.q_proj: 8
+model.layers.35.self_attn.v_proj: 8
+model.layers.1.mlp.down_proj: 4
+model.layers.8.mlp.down_proj: 8
+model.layers.13.self_attn.o_proj: 8
+model.layers.2.mlp.down_proj: 4
+model.layers.6.self_attn.o_proj: 8
+model.layers.9.mlp.down_proj: 8
+model.layers.5.self_attn.o_proj: 8
+model.layers.4.self_attn.o_proj: 8
+model.layers.5.mlp.down_proj: 8
+model.layers.3.self_attn.o_proj: 8
+model.layers.4.mlp.down_proj: 8
+model.layers.8.self_attn.o_proj: 8
+model.layers.0.self_attn.o_proj: 8
+model.layers.10.self_attn.o_proj: 8
+model.layers.2.self_attn.o_proj: 4
+model.layers.10.mlp.down_proj: 8
+model.layers.0.mlp.down_proj: 4
+model.layers.11.self_attn.o_proj: 8
+model.layers.11.mlp.down_proj: 8
+model.layers.12.self_attn.o_proj: 8
+model.layers.12.mlp.down_proj: 8
+model.layers.7.self_attn.o_proj: 8
+model.layers.1.self_attn.o_proj: 8
+model.layers.9.self_attn.o_proj: 8
+model.layers.3.mlp.down_proj: 4
+model.layers.7.mlp.down_proj: 8
+model.layers.6.mlp.down_proj: 8
+model.layers.25.self_attn.o_proj: 8
+model.layers.18.self_attn.o_proj: 8
+model.layers.28.mlp.down_proj: 4
+model.layers.19.self_attn.o_proj: 8
+model.layers.21.self_attn.o_proj: 8
+model.layers.16.self_attn.o_proj: 8
+model.layers.21.mlp.down_proj: 4
+model.layers.22.mlp.down_proj: 4
+model.layers.28.self_attn.o_proj: 8
+model.layers.35.mlp.down_proj: 8
+model.layers.23.mlp.down_proj: 8
+model.layers.15.mlp.down_proj: 4
+model.layers.20.self_attn.o_proj: 8
+model.layers.14.mlp.down_proj: 8
+model.layers.30.self_attn.o_proj: 8
+model.layers.30.mlp.down_proj: 4
+model.layers.33.self_attn.o_proj: 8
+model.layers.33.mlp.down_proj: 4
+model.layers.26.self_attn.o_proj: 8
+model.layers.29.mlp.down_proj: 4
+model.layers.15.self_attn.o_proj: 8
+model.layers.16.mlp.down_proj: 8
+model.layers.19.mlp.down_proj: 4
+model.layers.34.mlp.down_proj: 4
+model.layers.20.mlp.down_proj: 4
+model.layers.13.mlp.down_proj: 8
+model.layers.14.self_attn.o_proj: 8
+model.layers.31.self_attn.o_proj: 8
+model.layers.24.self_attn.o_proj: 8
+model.layers.18.mlp.down_proj: 4
+model.layers.23.self_attn.o_proj: 8
+model.layers.26.mlp.down_proj: 4
+model.layers.27.self_attn.o_proj: 8
+model.layers.17.self_attn.o_proj: 8
+model.layers.17.mlp.down_proj: 4
+model.layers.22.self_attn.o_proj: 8
+model.layers.24.mlp.down_proj: 8
+model.layers.27.mlp.down_proj: 4
+model.layers.31.mlp.down_proj: 4
+model.layers.25.mlp.down_proj: 4
+model.layers.32.self_attn.o_proj: 8
+model.layers.29.self_attn.o_proj: 8
+model.layers.32.mlp.down_proj: 4
+model.layers.35.self_attn.o_proj: 8
+model.layers.34.self_attn.o_proj: 8

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw6.96_4-8bit_grouped_seed1234/tokenizer_config.json

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/README.md

@@ -0,0 +1,18 @@
+# Quantized Model Checkpoint
+
+**Base model:** Qwen/Qwen3-8B
+
+**Average bitwidth:** 7.0062
+
+**Sensitivity method:** shapley
+
+**Constraints:**
+- max_kl: 0.01
+- min_eap: 0.985
+
+**Metrics:**
+- final_kl: 0.003705
+- final_eap: 0.985182
+- final_etl: 0.014818
+
+See `quantization_config.txt` for full configuration details.

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/added_tokens.json

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/chat_template.jinja

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/quantization_config.txt

@@ -0,0 +1,460 @@
+# Model: Qwen/Qwen3-8B
+# Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4bit_asym_8bit_sym_g128/Qwen3-8B
+# Sensitivity method: shapley
+# Estimation method: permutation
+# Available bitwidths: [4, 8]
+# Bitwidth map: {4: 4.156, 5: 5.156, 6: 6.156, 7: 7.156, 8: 8.156}
+#
+# Layer groups: 144 groups (fused layers share bitwidth)
+#   block_0:mlp.gate_proj,mlp.up_proj.block_0:mlp.gate_proj,mlp.up_proj: group 0, 2 layers
+#   block_0:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 1, 3 layers
+#   block_10:mlp.gate_proj,mlp.up_proj.block_10:mlp.gate_proj,mlp.up_proj: group 20, 2 layers
+#   block_10:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 21, 3 layers
+#   block_11:mlp.gate_proj,mlp.up_proj.block_11:mlp.gate_proj,mlp.up_proj: group 22, 2 layers
+#   block_11:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 23, 3 layers
+#   block_12:mlp.gate_proj,mlp.up_proj.block_12:mlp.gate_proj,mlp.up_proj: group 24, 2 layers
+#   block_12:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 25, 3 layers
+#   block_13:mlp.gate_proj,mlp.up_proj.block_13:mlp.gate_proj,mlp.up_proj: group 26, 2 layers
+#   block_13:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 27, 3 layers
+#   block_14:mlp.gate_proj,mlp.up_proj.block_14:mlp.gate_proj,mlp.up_proj: group 28, 2 layers
+#   block_14:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 29, 3 layers
+#   block_15:mlp.gate_proj,mlp.up_proj.block_15:mlp.gate_proj,mlp.up_proj: group 30, 2 layers
+#   block_15:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 31, 3 layers
+#   block_16:mlp.gate_proj,mlp.up_proj.block_16:mlp.gate_proj,mlp.up_proj: group 32, 2 layers
+#   block_16:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 33, 3 layers
+#   block_17:mlp.gate_proj,mlp.up_proj.block_17:mlp.gate_proj,mlp.up_proj: group 34, 2 layers
+#   block_17:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 35, 3 layers
+#   block_18:mlp.gate_proj,mlp.up_proj.block_18:mlp.gate_proj,mlp.up_proj: group 36, 2 layers
+#   block_18:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 37, 3 layers
+#   block_19:mlp.gate_proj,mlp.up_proj.block_19:mlp.gate_proj,mlp.up_proj: group 38, 2 layers
+#   block_19:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 39, 3 layers
+#   block_1:mlp.gate_proj,mlp.up_proj.block_1:mlp.gate_proj,mlp.up_proj: group 2, 2 layers
+#   block_1:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 3, 3 layers
+#   block_20:mlp.gate_proj,mlp.up_proj.block_20:mlp.gate_proj,mlp.up_proj: group 40, 2 layers
+#   block_20:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 41, 3 layers
+#   block_21:mlp.gate_proj,mlp.up_proj.block_21:mlp.gate_proj,mlp.up_proj: group 42, 2 layers
+#   block_21:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 43, 3 layers
+#   block_22:mlp.gate_proj,mlp.up_proj.block_22:mlp.gate_proj,mlp.up_proj: group 44, 2 layers
+#   block_22:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 45, 3 layers
+#   block_23:mlp.gate_proj,mlp.up_proj.block_23:mlp.gate_proj,mlp.up_proj: group 46, 2 layers
+#   block_23:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 47, 3 layers
+#   block_24:mlp.gate_proj,mlp.up_proj.block_24:mlp.gate_proj,mlp.up_proj: group 48, 2 layers
+#   block_24:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 49, 3 layers
+#   block_25:mlp.gate_proj,mlp.up_proj.block_25:mlp.gate_proj,mlp.up_proj: group 50, 2 layers
+#   block_25:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 51, 3 layers
+#   block_26:mlp.gate_proj,mlp.up_proj.block_26:mlp.gate_proj,mlp.up_proj: group 52, 2 layers
+#   block_26:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 53, 3 layers
+#   block_27:mlp.gate_proj,mlp.up_proj.block_27:mlp.gate_proj,mlp.up_proj: group 54, 2 layers
+#   block_27:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 55, 3 layers
+#   block_28:mlp.gate_proj,mlp.up_proj.block_28:mlp.gate_proj,mlp.up_proj: group 56, 2 layers
+#   block_28:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 57, 3 layers
+#   block_29:mlp.gate_proj,mlp.up_proj.block_29:mlp.gate_proj,mlp.up_proj: group 58, 2 layers
+#   block_29:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 59, 3 layers
+#   block_2:mlp.gate_proj,mlp.up_proj.block_2:mlp.gate_proj,mlp.up_proj: group 4, 2 layers
+#   block_2:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 5, 3 layers
+#   block_30:mlp.gate_proj,mlp.up_proj.block_30:mlp.gate_proj,mlp.up_proj: group 60, 2 layers
+#   block_30:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 61, 3 layers
+#   block_31:mlp.gate_proj,mlp.up_proj.block_31:mlp.gate_proj,mlp.up_proj: group 62, 2 layers
+#   block_31:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 63, 3 layers
+#   block_32:mlp.gate_proj,mlp.up_proj.block_32:mlp.gate_proj,mlp.up_proj: group 64, 2 layers
+#   block_32:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 65, 3 layers
+#   block_33:mlp.gate_proj,mlp.up_proj.block_33:mlp.gate_proj,mlp.up_proj: group 66, 2 layers
+#   block_33:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 67, 3 layers
+#   block_34:mlp.gate_proj,mlp.up_proj.block_34:mlp.gate_proj,mlp.up_proj: group 68, 2 layers
+#   block_34:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 69, 3 layers
+#   block_35:mlp.gate_proj,mlp.up_proj.block_35:mlp.gate_proj,mlp.up_proj: group 70, 2 layers
+#   block_35:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 71, 3 layers
+#   block_3:mlp.gate_proj,mlp.up_proj.block_3:mlp.gate_proj,mlp.up_proj: group 6, 2 layers
+#   block_3:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 7, 3 layers
+#   block_4:mlp.gate_proj,mlp.up_proj.block_4:mlp.gate_proj,mlp.up_proj: group 8, 2 layers
+#   block_4:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 9, 3 layers
+#   block_5:mlp.gate_proj,mlp.up_proj.block_5:mlp.gate_proj,mlp.up_proj: group 10, 2 layers
+#   block_5:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 11, 3 layers
+#   block_6:mlp.gate_proj,mlp.up_proj.block_6:mlp.gate_proj,mlp.up_proj: group 12, 2 layers
+#   block_6:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 13, 3 layers
+#   block_7:mlp.gate_proj,mlp.up_proj.block_7:mlp.gate_proj,mlp.up_proj: group 14, 2 layers
+#   block_7:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 15, 3 layers
+#   block_8:mlp.gate_proj,mlp.up_proj.block_8:mlp.gate_proj,mlp.up_proj: group 16, 2 layers
+#   block_8:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 17, 3 layers
+#   block_9:mlp.gate_proj,mlp.up_proj.block_9:mlp.gate_proj,mlp.up_proj: group 18, 2 layers
+#   block_9:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 19, 3 layers
+#   Fused in model.layers.0:
+#     - self_attn.o_proj (group 84, 1 layers)
+#     - mlp.down_proj (group 88, 1 layers)
+#   Fused in model.layers.1:
+#     - mlp.down_proj (group 72, 1 layers)
+#     - self_attn.o_proj (group 94, 1 layers)
+#   Fused in model.layers.10:
+#     - self_attn.o_proj (group 85, 1 layers)
+#     - mlp.down_proj (group 87, 1 layers)
+#   Fused in model.layers.11:
+#     - self_attn.o_proj (group 89, 1 layers)
+#     - mlp.down_proj (group 90, 1 layers)
+#   Fused in model.layers.12:
+#     - self_attn.o_proj (group 91, 1 layers)
+#     - mlp.down_proj (group 92, 1 layers)
+#   Fused in model.layers.13:
+#     - self_attn.o_proj (group 74, 1 layers)
+#     - mlp.down_proj (group 124, 1 layers)
+#   Fused in model.layers.14:
+#     - mlp.down_proj (group 112, 1 layers)
+#     - self_attn.o_proj (group 125, 1 layers)
+#   Fused in model.layers.15:
+#     - mlp.down_proj (group 110, 1 layers)
+#     - self_attn.o_proj (group 119, 1 layers)
+#   Fused in model.layers.16:
+#     - self_attn.o_proj (group 104, 1 layers)
+#     - mlp.down_proj (group 120, 1 layers)
+#   Fused in model.layers.17:
+#     - self_attn.o_proj (group 132, 1 layers)
+#     - mlp.down_proj (group 133, 1 layers)
+#   Fused in model.layers.18:
+#     - self_attn.o_proj (group 100, 1 layers)
+#     - mlp.down_proj (group 128, 1 layers)
+#   Fused in model.layers.19:
+#     - self_attn.o_proj (group 102, 1 layers)
+#     - mlp.down_proj (group 121, 1 layers)
+#   Fused in model.layers.2:
+#     - mlp.down_proj (group 75, 1 layers)
+#     - self_attn.o_proj (group 86, 1 layers)
+#   Fused in model.layers.20:
+#     - self_attn.o_proj (group 111, 1 layers)
+#     - mlp.down_proj (group 123, 1 layers)
+#   Fused in model.layers.21:
+#     - self_attn.o_proj (group 103, 1 layers)
+#     - mlp.down_proj (group 105, 1 layers)
+#   Fused in model.layers.22:
+#     - mlp.down_proj (group 106, 1 layers)
+#     - self_attn.o_proj (group 134, 1 layers)
+#   Fused in model.layers.23:
+#     - mlp.down_proj (group 109, 1 layers)
+#     - self_attn.o_proj (group 129, 1 layers)
+#   Fused in model.layers.24:
+#     - self_attn.o_proj (group 127, 1 layers)
+#     - mlp.down_proj (group 135, 1 layers)
+#   Fused in model.layers.25:
+#     - self_attn.o_proj (group 99, 1 layers)
+#     - mlp.down_proj (group 138, 1 layers)
+#   Fused in model.layers.26:
+#     - self_attn.o_proj (group 117, 1 layers)
+#     - mlp.down_proj (group 130, 1 layers)
+#   Fused in model.layers.27:
+#     - self_attn.o_proj (group 131, 1 layers)
+#     - mlp.down_proj (group 136, 1 layers)
+#   Fused in model.layers.28:
+#     - mlp.down_proj (group 101, 1 layers)
+#     - self_attn.o_proj (group 107, 1 layers)
+#   Fused in model.layers.29:
+#     - mlp.down_proj (group 118, 1 layers)
+#     - self_attn.o_proj (group 140, 1 layers)
+#   Fused in model.layers.3:
+#     - self_attn.o_proj (group 81, 1 layers)
+#     - mlp.down_proj (group 96, 1 layers)
+#   Fused in model.layers.30:
+#     - self_attn.o_proj (group 113, 1 layers)
+#     - mlp.down_proj (group 114, 1 layers)
+#   Fused in model.layers.31:
+#     - self_attn.o_proj (group 126, 1 layers)
+#     - mlp.down_proj (group 137, 1 layers)
+#   Fused in model.layers.32:
+#     - self_attn.o_proj (group 139, 1 layers)
+#     - mlp.down_proj (group 141, 1 layers)
+#   Fused in model.layers.33:
+#     - self_attn.o_proj (group 115, 1 layers)
+#     - mlp.down_proj (group 116, 1 layers)
+#   Fused in model.layers.34:
+#     - mlp.down_proj (group 122, 1 layers)
+#     - self_attn.o_proj (group 143, 1 layers)
+#   Fused in model.layers.35:
+#     - mlp.down_proj (group 108, 1 layers)
+#     - self_attn.o_proj (group 142, 1 layers)
+#   Fused in model.layers.4:
+#     - self_attn.o_proj (group 79, 1 layers)
+#     - mlp.down_proj (group 82, 1 layers)
+#   Fused in model.layers.5:
+#     - self_attn.o_proj (group 78, 1 layers)
+#     - mlp.down_proj (group 80, 1 layers)
+#   Fused in model.layers.6:
+#     - self_attn.o_proj (group 76, 1 layers)
+#     - mlp.down_proj (group 98, 1 layers)
+#   Fused in model.layers.7:
+#     - self_attn.o_proj (group 93, 1 layers)
+#     - mlp.down_proj (group 97, 1 layers)
+#   Fused in model.layers.8:
+#     - mlp.down_proj (group 73, 1 layers)
+#     - self_attn.o_proj (group 83, 1 layers)
+#   Fused in model.layers.9:
+#     - mlp.down_proj (group 77, 1 layers)
+#     - self_attn.o_proj (group 95, 1 layers)
+#
+# Mode: binary_search_constraint (measured)
+# Constraint max_kl: 0.01
+# Constraint min_eap: 0.985
+# Weights: nll=0.0, kl=0.0, eap=1.0
+#
+# Average bitwidth: 7.0062
+# Total params: 6945767424
+# Total bits: 48663724294
+# Final KL: 0.003705
+# Final EAP: 0.985182
+# Final ETL: 0.014818
+# Satisfies constraints: True
+# Solver calls: 9
+# Evaluations: 9
+#
+# Bitwidth distribution:
+#   8-bit: 211 layers (83.7%)
+#   4-bit: 41 layers (16.3%)
+#
+model.layers.0.mlp.gate_proj: 4
+model.layers.0.mlp.up_proj: 4
+model.layers.0.self_attn.k_proj: 8
+model.layers.0.self_attn.q_proj: 8
+model.layers.0.self_attn.v_proj: 8
+model.layers.1.mlp.gate_proj: 4
+model.layers.1.mlp.up_proj: 4
+model.layers.1.self_attn.k_proj: 8
+model.layers.1.self_attn.q_proj: 8
+model.layers.1.self_attn.v_proj: 8
+model.layers.2.mlp.gate_proj: 4
+model.layers.2.mlp.up_proj: 4
+model.layers.2.self_attn.k_proj: 8
+model.layers.2.self_attn.q_proj: 8
+model.layers.2.self_attn.v_proj: 8
+model.layers.3.mlp.gate_proj: 4
+model.layers.3.mlp.up_proj: 4
+model.layers.3.self_attn.k_proj: 8
+model.layers.3.self_attn.q_proj: 8
+model.layers.3.self_attn.v_proj: 8
+model.layers.4.mlp.gate_proj: 4
+model.layers.4.mlp.up_proj: 4
+model.layers.4.self_attn.k_proj: 8
+model.layers.4.self_attn.q_proj: 8
+model.layers.4.self_attn.v_proj: 8
+model.layers.5.mlp.gate_proj: 4
+model.layers.5.mlp.up_proj: 4
+model.layers.5.self_attn.k_proj: 8
+model.layers.5.self_attn.q_proj: 8
+model.layers.5.self_attn.v_proj: 8
+model.layers.6.mlp.gate_proj: 8
+model.layers.6.mlp.up_proj: 8
+model.layers.6.self_attn.k_proj: 8
+model.layers.6.self_attn.q_proj: 8
+model.layers.6.self_attn.v_proj: 8
+model.layers.7.mlp.gate_proj: 8
+model.layers.7.mlp.up_proj: 8
+model.layers.7.self_attn.k_proj: 8
+model.layers.7.self_attn.q_proj: 8
+model.layers.7.self_attn.v_proj: 8
+model.layers.8.mlp.gate_proj: 8
+model.layers.8.mlp.up_proj: 8
+model.layers.8.self_attn.k_proj: 8
+model.layers.8.self_attn.q_proj: 8
+model.layers.8.self_attn.v_proj: 8
+model.layers.9.mlp.gate_proj: 8
+model.layers.9.mlp.up_proj: 8
+model.layers.9.self_attn.k_proj: 8
+model.layers.9.self_attn.q_proj: 8
+model.layers.9.self_attn.v_proj: 8
+model.layers.10.mlp.gate_proj: 8
+model.layers.10.mlp.up_proj: 8
+model.layers.10.self_attn.k_proj: 8
+model.layers.10.self_attn.q_proj: 8
+model.layers.10.self_attn.v_proj: 8
+model.layers.11.mlp.gate_proj: 8
+model.layers.11.mlp.up_proj: 8
+model.layers.11.self_attn.k_proj: 8
+model.layers.11.self_attn.q_proj: 8
+model.layers.11.self_attn.v_proj: 8
+model.layers.12.mlp.gate_proj: 8
+model.layers.12.mlp.up_proj: 8
+model.layers.12.self_attn.k_proj: 8
+model.layers.12.self_attn.q_proj: 8
+model.layers.12.self_attn.v_proj: 8
+model.layers.13.mlp.gate_proj: 8
+model.layers.13.mlp.up_proj: 8
+model.layers.13.self_attn.k_proj: 8
+model.layers.13.self_attn.q_proj: 8
+model.layers.13.self_attn.v_proj: 8
+model.layers.14.mlp.gate_proj: 8
+model.layers.14.mlp.up_proj: 8
+model.layers.14.self_attn.k_proj: 8
+model.layers.14.self_attn.q_proj: 8
+model.layers.14.self_attn.v_proj: 8
+model.layers.15.mlp.gate_proj: 8
+model.layers.15.mlp.up_proj: 8
+model.layers.15.self_attn.k_proj: 8
+model.layers.15.self_attn.q_proj: 8
+model.layers.15.self_attn.v_proj: 8
+model.layers.16.mlp.gate_proj: 8
+model.layers.16.mlp.up_proj: 8
+model.layers.16.self_attn.k_proj: 8
+model.layers.16.self_attn.q_proj: 8
+model.layers.16.self_attn.v_proj: 8
+model.layers.17.mlp.gate_proj: 8
+model.layers.17.mlp.up_proj: 8
+model.layers.17.self_attn.k_proj: 8
+model.layers.17.self_attn.q_proj: 8
+model.layers.17.self_attn.v_proj: 8
+model.layers.18.mlp.gate_proj: 8
+model.layers.18.mlp.up_proj: 8
+model.layers.18.self_attn.k_proj: 8
+model.layers.18.self_attn.q_proj: 8
+model.layers.18.self_attn.v_proj: 8
+model.layers.19.mlp.gate_proj: 8
+model.layers.19.mlp.up_proj: 8
+model.layers.19.self_attn.k_proj: 8
+model.layers.19.self_attn.q_proj: 8
+model.layers.19.self_attn.v_proj: 8
+model.layers.20.mlp.gate_proj: 8
+model.layers.20.mlp.up_proj: 8
+model.layers.20.self_attn.k_proj: 8
+model.layers.20.self_attn.q_proj: 8
+model.layers.20.self_attn.v_proj: 8
+model.layers.21.mlp.gate_proj: 8
+model.layers.21.mlp.up_proj: 8
+model.layers.21.self_attn.k_proj: 8
+model.layers.21.self_attn.q_proj: 8
+model.layers.21.self_attn.v_proj: 8
+model.layers.22.mlp.gate_proj: 8
+model.layers.22.mlp.up_proj: 8
+model.layers.22.self_attn.k_proj: 8
+model.layers.22.self_attn.q_proj: 8
+model.layers.22.self_attn.v_proj: 8
+model.layers.23.mlp.gate_proj: 4
+model.layers.23.mlp.up_proj: 4
+model.layers.23.self_attn.k_proj: 8
+model.layers.23.self_attn.q_proj: 8
+model.layers.23.self_attn.v_proj: 8
+model.layers.24.mlp.gate_proj: 8
+model.layers.24.mlp.up_proj: 8
+model.layers.24.self_attn.k_proj: 8
+model.layers.24.self_attn.q_proj: 8
+model.layers.24.self_attn.v_proj: 8
+model.layers.25.mlp.gate_proj: 4
+model.layers.25.mlp.up_proj: 4
+model.layers.25.self_attn.k_proj: 8
+model.layers.25.self_attn.q_proj: 8
+model.layers.25.self_attn.v_proj: 8
+model.layers.26.mlp.gate_proj: 4
+model.layers.26.mlp.up_proj: 4
+model.layers.26.self_attn.k_proj: 8
+model.layers.26.self_attn.q_proj: 8
+model.layers.26.self_attn.v_proj: 8
+model.layers.27.mlp.gate_proj: 8
+model.layers.27.mlp.up_proj: 8
+model.layers.27.self_attn.k_proj: 8
+model.layers.27.self_attn.q_proj: 8
+model.layers.27.self_attn.v_proj: 8
+model.layers.28.mlp.gate_proj: 8
+model.layers.28.mlp.up_proj: 8
+model.layers.28.self_attn.k_proj: 8
+model.layers.28.self_attn.q_proj: 8
+model.layers.28.self_attn.v_proj: 8
+model.layers.29.mlp.gate_proj: 8
+model.layers.29.mlp.up_proj: 8
+model.layers.29.self_attn.k_proj: 8
+model.layers.29.self_attn.q_proj: 8
+model.layers.29.self_attn.v_proj: 8
+model.layers.30.mlp.gate_proj: 8
+model.layers.30.mlp.up_proj: 8
+model.layers.30.self_attn.k_proj: 8
+model.layers.30.self_attn.q_proj: 8
+model.layers.30.self_attn.v_proj: 8
+model.layers.31.mlp.gate_proj: 8
+model.layers.31.mlp.up_proj: 8
+model.layers.31.self_attn.k_proj: 8
+model.layers.31.self_attn.q_proj: 8
+model.layers.31.self_attn.v_proj: 8
+model.layers.32.mlp.gate_proj: 8
+model.layers.32.mlp.up_proj: 8
+model.layers.32.self_attn.k_proj: 8
+model.layers.32.self_attn.q_proj: 8
+model.layers.32.self_attn.v_proj: 8
+model.layers.33.mlp.gate_proj: 8
+model.layers.33.mlp.up_proj: 8
+model.layers.33.self_attn.k_proj: 8
+model.layers.33.self_attn.q_proj: 8
+model.layers.33.self_attn.v_proj: 8
+model.layers.34.mlp.gate_proj: 8
+model.layers.34.mlp.up_proj: 8
+model.layers.34.self_attn.k_proj: 8
+model.layers.34.self_attn.q_proj: 8
+model.layers.34.self_attn.v_proj: 8
+model.layers.35.mlp.gate_proj: 8
+model.layers.35.mlp.up_proj: 8
+model.layers.35.self_attn.k_proj: 8
+model.layers.35.self_attn.q_proj: 8
+model.layers.35.self_attn.v_proj: 8
+model.layers.1.mlp.down_proj: 4
+model.layers.8.mlp.down_proj: 8
+model.layers.13.self_attn.o_proj: 8
+model.layers.2.mlp.down_proj: 4
+model.layers.6.self_attn.o_proj: 8
+model.layers.9.mlp.down_proj: 8
+model.layers.5.self_attn.o_proj: 8
+model.layers.4.self_attn.o_proj: 4
+model.layers.5.mlp.down_proj: 8
+model.layers.3.self_attn.o_proj: 8
+model.layers.4.mlp.down_proj: 8
+model.layers.8.self_attn.o_proj: 8
+model.layers.0.self_attn.o_proj: 8
+model.layers.10.self_attn.o_proj: 8
+model.layers.2.self_attn.o_proj: 4
+model.layers.10.mlp.down_proj: 8
+model.layers.0.mlp.down_proj: 4
+model.layers.11.self_attn.o_proj: 8
+model.layers.11.mlp.down_proj: 8
+model.layers.12.self_attn.o_proj: 8
+model.layers.12.mlp.down_proj: 8
+model.layers.7.self_attn.o_proj: 8
+model.layers.1.self_attn.o_proj: 8
+model.layers.9.self_attn.o_proj: 8
+model.layers.3.mlp.down_proj: 4
+model.layers.7.mlp.down_proj: 8
+model.layers.6.mlp.down_proj: 8
+model.layers.25.self_attn.o_proj: 8
+model.layers.18.self_attn.o_proj: 8
+model.layers.28.mlp.down_proj: 4
+model.layers.19.self_attn.o_proj: 8
+model.layers.21.self_attn.o_proj: 8
+model.layers.16.self_attn.o_proj: 8
+model.layers.21.mlp.down_proj: 4
+model.layers.22.mlp.down_proj: 4
+model.layers.28.self_attn.o_proj: 8
+model.layers.35.mlp.down_proj: 8
+model.layers.23.mlp.down_proj: 8
+model.layers.15.mlp.down_proj: 4
+model.layers.20.self_attn.o_proj: 8
+model.layers.14.mlp.down_proj: 8
+model.layers.30.self_attn.o_proj: 8
+model.layers.30.mlp.down_proj: 4
+model.layers.33.self_attn.o_proj: 8
+model.layers.33.mlp.down_proj: 4
+model.layers.26.self_attn.o_proj: 8
+model.layers.29.mlp.down_proj: 4
+model.layers.15.self_attn.o_proj: 8
+model.layers.16.mlp.down_proj: 8
+model.layers.19.mlp.down_proj: 4
+model.layers.34.mlp.down_proj: 4
+model.layers.20.mlp.down_proj: 4
+model.layers.13.mlp.down_proj: 8
+model.layers.14.self_attn.o_proj: 8
+model.layers.31.self_attn.o_proj: 8
+model.layers.24.self_attn.o_proj: 8
+model.layers.18.mlp.down_proj: 4
+model.layers.23.self_attn.o_proj: 8
+model.layers.26.mlp.down_proj: 4
+model.layers.27.self_attn.o_proj: 8
+model.layers.17.self_attn.o_proj: 8
+model.layers.17.mlp.down_proj: 4
+model.layers.22.self_attn.o_proj: 8
+model.layers.24.mlp.down_proj: 8
+model.layers.27.mlp.down_proj: 4
+model.layers.31.mlp.down_proj: 4
+model.layers.25.mlp.down_proj: 4
+model.layers.32.self_attn.o_proj: 8
+model.layers.29.self_attn.o_proj: 8
+model.layers.32.mlp.down_proj: 4
+model.layers.35.self_attn.o_proj: 8
+model.layers.34.self_attn.o_proj: 8

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.985_sha_bw7.01_4-8bit_grouped_seed42/tokenizer_config.json

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/README.md

@@ -0,0 +1,18 @@
+# Quantized Model Checkpoint
+
+**Base model:** Qwen/Qwen3-8B
+
+**Average bitwidth:** 7.5956
+
+**Sensitivity method:** shapley
+
+**Constraints:**
+- max_kl: 0.01
+- min_eap: 0.99
+
+**Metrics:**
+- final_kl: 0.001538
+- final_eap: 0.990155
+- final_etl: 0.009845
+
+See `quantization_config.txt` for full configuration details.

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/added_tokens.json

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/chat_template.jinja

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/quantization_config.txt

@@ -0,0 +1,460 @@
+# Model: Qwen/Qwen3-8B
+# Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4bit_asym_8bit_sym_g128/Qwen3-8B
+# Sensitivity method: shapley
+# Estimation method: permutation
+# Available bitwidths: [4, 8]
+# Bitwidth map: {4: 4.156, 5: 5.156, 6: 6.156, 7: 7.156, 8: 8.156}
+#
+# Layer groups: 144 groups (fused layers share bitwidth)
+#   block_0:mlp.gate_proj,mlp.up_proj.block_0:mlp.gate_proj,mlp.up_proj: group 0, 2 layers
+#   block_0:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 1, 3 layers
+#   block_10:mlp.gate_proj,mlp.up_proj.block_10:mlp.gate_proj,mlp.up_proj: group 20, 2 layers
+#   block_10:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 21, 3 layers
+#   block_11:mlp.gate_proj,mlp.up_proj.block_11:mlp.gate_proj,mlp.up_proj: group 22, 2 layers
+#   block_11:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 23, 3 layers
+#   block_12:mlp.gate_proj,mlp.up_proj.block_12:mlp.gate_proj,mlp.up_proj: group 24, 2 layers
+#   block_12:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 25, 3 layers
+#   block_13:mlp.gate_proj,mlp.up_proj.block_13:mlp.gate_proj,mlp.up_proj: group 26, 2 layers
+#   block_13:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 27, 3 layers
+#   block_14:mlp.gate_proj,mlp.up_proj.block_14:mlp.gate_proj,mlp.up_proj: group 28, 2 layers
+#   block_14:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 29, 3 layers
+#   block_15:mlp.gate_proj,mlp.up_proj.block_15:mlp.gate_proj,mlp.up_proj: group 30, 2 layers
+#   block_15:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 31, 3 layers
+#   block_16:mlp.gate_proj,mlp.up_proj.block_16:mlp.gate_proj,mlp.up_proj: group 32, 2 layers
+#   block_16:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 33, 3 layers
+#   block_17:mlp.gate_proj,mlp.up_proj.block_17:mlp.gate_proj,mlp.up_proj: group 34, 2 layers
+#   block_17:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 35, 3 layers
+#   block_18:mlp.gate_proj,mlp.up_proj.block_18:mlp.gate_proj,mlp.up_proj: group 36, 2 layers
+#   block_18:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 37, 3 layers
+#   block_19:mlp.gate_proj,mlp.up_proj.block_19:mlp.gate_proj,mlp.up_proj: group 38, 2 layers
+#   block_19:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 39, 3 layers
+#   block_1:mlp.gate_proj,mlp.up_proj.block_1:mlp.gate_proj,mlp.up_proj: group 2, 2 layers
+#   block_1:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 3, 3 layers
+#   block_20:mlp.gate_proj,mlp.up_proj.block_20:mlp.gate_proj,mlp.up_proj: group 40, 2 layers
+#   block_20:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 41, 3 layers
+#   block_21:mlp.gate_proj,mlp.up_proj.block_21:mlp.gate_proj,mlp.up_proj: group 42, 2 layers
+#   block_21:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 43, 3 layers
+#   block_22:mlp.gate_proj,mlp.up_proj.block_22:mlp.gate_proj,mlp.up_proj: group 44, 2 layers
+#   block_22:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 45, 3 layers
+#   block_23:mlp.gate_proj,mlp.up_proj.block_23:mlp.gate_proj,mlp.up_proj: group 46, 2 layers
+#   block_23:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 47, 3 layers
+#   block_24:mlp.gate_proj,mlp.up_proj.block_24:mlp.gate_proj,mlp.up_proj: group 48, 2 layers
+#   block_24:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 49, 3 layers
+#   block_25:mlp.gate_proj,mlp.up_proj.block_25:mlp.gate_proj,mlp.up_proj: group 50, 2 layers
+#   block_25:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 51, 3 layers
+#   block_26:mlp.gate_proj,mlp.up_proj.block_26:mlp.gate_proj,mlp.up_proj: group 52, 2 layers
+#   block_26:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 53, 3 layers
+#   block_27:mlp.gate_proj,mlp.up_proj.block_27:mlp.gate_proj,mlp.up_proj: group 54, 2 layers
+#   block_27:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 55, 3 layers
+#   block_28:mlp.gate_proj,mlp.up_proj.block_28:mlp.gate_proj,mlp.up_proj: group 56, 2 layers
+#   block_28:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 57, 3 layers
+#   block_29:mlp.gate_proj,mlp.up_proj.block_29:mlp.gate_proj,mlp.up_proj: group 58, 2 layers
+#   block_29:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 59, 3 layers
+#   block_2:mlp.gate_proj,mlp.up_proj.block_2:mlp.gate_proj,mlp.up_proj: group 4, 2 layers
+#   block_2:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 5, 3 layers
+#   block_30:mlp.gate_proj,mlp.up_proj.block_30:mlp.gate_proj,mlp.up_proj: group 60, 2 layers
+#   block_30:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 61, 3 layers
+#   block_31:mlp.gate_proj,mlp.up_proj.block_31:mlp.gate_proj,mlp.up_proj: group 62, 2 layers
+#   block_31:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 63, 3 layers
+#   block_32:mlp.gate_proj,mlp.up_proj.block_32:mlp.gate_proj,mlp.up_proj: group 64, 2 layers
+#   block_32:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 65, 3 layers
+#   block_33:mlp.gate_proj,mlp.up_proj.block_33:mlp.gate_proj,mlp.up_proj: group 66, 2 layers
+#   block_33:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 67, 3 layers
+#   block_34:mlp.gate_proj,mlp.up_proj.block_34:mlp.gate_proj,mlp.up_proj: group 68, 2 layers
+#   block_34:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 69, 3 layers
+#   block_35:mlp.gate_proj,mlp.up_proj.block_35:mlp.gate_proj,mlp.up_proj: group 70, 2 layers
+#   block_35:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 71, 3 layers
+#   block_3:mlp.gate_proj,mlp.up_proj.block_3:mlp.gate_proj,mlp.up_proj: group 6, 2 layers
+#   block_3:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 7, 3 layers
+#   block_4:mlp.gate_proj,mlp.up_proj.block_4:mlp.gate_proj,mlp.up_proj: group 8, 2 layers
+#   block_4:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 9, 3 layers
+#   block_5:mlp.gate_proj,mlp.up_proj.block_5:mlp.gate_proj,mlp.up_proj: group 10, 2 layers
+#   block_5:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 11, 3 layers
+#   block_6:mlp.gate_proj,mlp.up_proj.block_6:mlp.gate_proj,mlp.up_proj: group 12, 2 layers
+#   block_6:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 13, 3 layers
+#   block_7:mlp.gate_proj,mlp.up_proj.block_7:mlp.gate_proj,mlp.up_proj: group 14, 2 layers
+#   block_7:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 15, 3 layers
+#   block_8:mlp.gate_proj,mlp.up_proj.block_8:mlp.gate_proj,mlp.up_proj: group 16, 2 layers
+#   block_8:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 17, 3 layers
+#   block_9:mlp.gate_proj,mlp.up_proj.block_9:mlp.gate_proj,mlp.up_proj: group 18, 2 layers
+#   block_9:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 19, 3 layers
+#   Fused in model.layers.0:
+#     - self_attn.o_proj (group 84, 1 layers)
+#     - mlp.down_proj (group 88, 1 layers)
+#   Fused in model.layers.1:
+#     - mlp.down_proj (group 72, 1 layers)
+#     - self_attn.o_proj (group 94, 1 layers)
+#   Fused in model.layers.10:
+#     - self_attn.o_proj (group 85, 1 layers)
+#     - mlp.down_proj (group 87, 1 layers)
+#   Fused in model.layers.11:
+#     - self_attn.o_proj (group 89, 1 layers)
+#     - mlp.down_proj (group 90, 1 layers)
+#   Fused in model.layers.12:
+#     - self_attn.o_proj (group 91, 1 layers)
+#     - mlp.down_proj (group 92, 1 layers)
+#   Fused in model.layers.13:
+#     - self_attn.o_proj (group 74, 1 layers)
+#     - mlp.down_proj (group 124, 1 layers)
+#   Fused in model.layers.14:
+#     - mlp.down_proj (group 112, 1 layers)
+#     - self_attn.o_proj (group 125, 1 layers)
+#   Fused in model.layers.15:
+#     - mlp.down_proj (group 110, 1 layers)
+#     - self_attn.o_proj (group 119, 1 layers)
+#   Fused in model.layers.16:
+#     - self_attn.o_proj (group 104, 1 layers)
+#     - mlp.down_proj (group 120, 1 layers)
+#   Fused in model.layers.17:
+#     - self_attn.o_proj (group 132, 1 layers)
+#     - mlp.down_proj (group 133, 1 layers)
+#   Fused in model.layers.18:
+#     - self_attn.o_proj (group 100, 1 layers)
+#     - mlp.down_proj (group 128, 1 layers)
+#   Fused in model.layers.19:
+#     - self_attn.o_proj (group 102, 1 layers)
+#     - mlp.down_proj (group 121, 1 layers)
+#   Fused in model.layers.2:
+#     - mlp.down_proj (group 75, 1 layers)
+#     - self_attn.o_proj (group 86, 1 layers)
+#   Fused in model.layers.20:
+#     - self_attn.o_proj (group 111, 1 layers)
+#     - mlp.down_proj (group 123, 1 layers)
+#   Fused in model.layers.21:
+#     - self_attn.o_proj (group 103, 1 layers)
+#     - mlp.down_proj (group 105, 1 layers)
+#   Fused in model.layers.22:
+#     - mlp.down_proj (group 106, 1 layers)
+#     - self_attn.o_proj (group 134, 1 layers)
+#   Fused in model.layers.23:
+#     - mlp.down_proj (group 109, 1 layers)
+#     - self_attn.o_proj (group 129, 1 layers)
+#   Fused in model.layers.24:
+#     - self_attn.o_proj (group 127, 1 layers)
+#     - mlp.down_proj (group 135, 1 layers)
+#   Fused in model.layers.25:
+#     - self_attn.o_proj (group 99, 1 layers)
+#     - mlp.down_proj (group 138, 1 layers)
+#   Fused in model.layers.26:
+#     - self_attn.o_proj (group 117, 1 layers)
+#     - mlp.down_proj (group 130, 1 layers)
+#   Fused in model.layers.27:
+#     - self_attn.o_proj (group 131, 1 layers)
+#     - mlp.down_proj (group 136, 1 layers)
+#   Fused in model.layers.28:
+#     - mlp.down_proj (group 101, 1 layers)
+#     - self_attn.o_proj (group 107, 1 layers)
+#   Fused in model.layers.29:
+#     - mlp.down_proj (group 118, 1 layers)
+#     - self_attn.o_proj (group 140, 1 layers)
+#   Fused in model.layers.3:
+#     - self_attn.o_proj (group 81, 1 layers)
+#     - mlp.down_proj (group 96, 1 layers)
+#   Fused in model.layers.30:
+#     - self_attn.o_proj (group 113, 1 layers)
+#     - mlp.down_proj (group 114, 1 layers)
+#   Fused in model.layers.31:
+#     - self_attn.o_proj (group 126, 1 layers)
+#     - mlp.down_proj (group 137, 1 layers)
+#   Fused in model.layers.32:
+#     - self_attn.o_proj (group 139, 1 layers)
+#     - mlp.down_proj (group 141, 1 layers)
+#   Fused in model.layers.33:
+#     - self_attn.o_proj (group 115, 1 layers)
+#     - mlp.down_proj (group 116, 1 layers)
+#   Fused in model.layers.34:
+#     - mlp.down_proj (group 122, 1 layers)
+#     - self_attn.o_proj (group 143, 1 layers)
+#   Fused in model.layers.35:
+#     - mlp.down_proj (group 108, 1 layers)
+#     - self_attn.o_proj (group 142, 1 layers)
+#   Fused in model.layers.4:
+#     - self_attn.o_proj (group 79, 1 layers)
+#     - mlp.down_proj (group 82, 1 layers)
+#   Fused in model.layers.5:
+#     - self_attn.o_proj (group 78, 1 layers)
+#     - mlp.down_proj (group 80, 1 layers)
+#   Fused in model.layers.6:
+#     - self_attn.o_proj (group 76, 1 layers)
+#     - mlp.down_proj (group 98, 1 layers)
+#   Fused in model.layers.7:
+#     - self_attn.o_proj (group 93, 1 layers)
+#     - mlp.down_proj (group 97, 1 layers)
+#   Fused in model.layers.8:
+#     - mlp.down_proj (group 73, 1 layers)
+#     - self_attn.o_proj (group 83, 1 layers)
+#   Fused in model.layers.9:
+#     - mlp.down_proj (group 77, 1 layers)
+#     - self_attn.o_proj (group 95, 1 layers)
+#
+# Mode: binary_search_constraint (measured)
+# Constraint max_kl: 0.01
+# Constraint min_eap: 0.99
+# Weights: nll=0.0, kl=0.0, eap=1.0
+#
+# Average bitwidth: 7.5956
+# Total params: 6945767424
+# Total bits: 52757364998
+# Final KL: 0.001538
+# Final EAP: 0.990155
+# Final ETL: 0.009845
+# Satisfies constraints: True
+# Solver calls: 9
+# Evaluations: 9
+#
+# Bitwidth distribution:
+#   8-bit: 232 layers (92.1%)
+#   4-bit: 20 layers (7.9%)
+#
+model.layers.0.mlp.gate_proj: 4
+model.layers.0.mlp.up_proj: 4
+model.layers.0.self_attn.k_proj: 8
+model.layers.0.self_attn.q_proj: 8
+model.layers.0.self_attn.v_proj: 8
+model.layers.1.mlp.gate_proj: 4
+model.layers.1.mlp.up_proj: 4
+model.layers.1.self_attn.k_proj: 8
+model.layers.1.self_attn.q_proj: 8
+model.layers.1.self_attn.v_proj: 8
+model.layers.2.mlp.gate_proj: 4
+model.layers.2.mlp.up_proj: 4
+model.layers.2.self_attn.k_proj: 8
+model.layers.2.self_attn.q_proj: 8
+model.layers.2.self_attn.v_proj: 8
+model.layers.3.mlp.gate_proj: 4
+model.layers.3.mlp.up_proj: 4
+model.layers.3.self_attn.k_proj: 8
+model.layers.3.self_attn.q_proj: 8
+model.layers.3.self_attn.v_proj: 8
+model.layers.4.mlp.gate_proj: 8
+model.layers.4.mlp.up_proj: 8
+model.layers.4.self_attn.k_proj: 8
+model.layers.4.self_attn.q_proj: 8
+model.layers.4.self_attn.v_proj: 8
+model.layers.5.mlp.gate_proj: 8
+model.layers.5.mlp.up_proj: 8
+model.layers.5.self_attn.k_proj: 8
+model.layers.5.self_attn.q_proj: 8
+model.layers.5.self_attn.v_proj: 8
+model.layers.6.mlp.gate_proj: 8
+model.layers.6.mlp.up_proj: 8
+model.layers.6.self_attn.k_proj: 8
+model.layers.6.self_attn.q_proj: 8
+model.layers.6.self_attn.v_proj: 8
+model.layers.7.mlp.gate_proj: 8
+model.layers.7.mlp.up_proj: 8
+model.layers.7.self_attn.k_proj: 8
+model.layers.7.self_attn.q_proj: 8
+model.layers.7.self_attn.v_proj: 8
+model.layers.8.mlp.gate_proj: 8
+model.layers.8.mlp.up_proj: 8
+model.layers.8.self_attn.k_proj: 8
+model.layers.8.self_attn.q_proj: 8
+model.layers.8.self_attn.v_proj: 8
+model.layers.9.mlp.gate_proj: 8
+model.layers.9.mlp.up_proj: 8
+model.layers.9.self_attn.k_proj: 8
+model.layers.9.self_attn.q_proj: 8
+model.layers.9.self_attn.v_proj: 8
+model.layers.10.mlp.gate_proj: 8
+model.layers.10.mlp.up_proj: 8
+model.layers.10.self_attn.k_proj: 8
+model.layers.10.self_attn.q_proj: 8
+model.layers.10.self_attn.v_proj: 8
+model.layers.11.mlp.gate_proj: 8
+model.layers.11.mlp.up_proj: 8
+model.layers.11.self_attn.k_proj: 8
+model.layers.11.self_attn.q_proj: 8
+model.layers.11.self_attn.v_proj: 8
+model.layers.12.mlp.gate_proj: 8
+model.layers.12.mlp.up_proj: 8
+model.layers.12.self_attn.k_proj: 8
+model.layers.12.self_attn.q_proj: 8
+model.layers.12.self_attn.v_proj: 8
+model.layers.13.mlp.gate_proj: 8
+model.layers.13.mlp.up_proj: 8
+model.layers.13.self_attn.k_proj: 8
+model.layers.13.self_attn.q_proj: 8
+model.layers.13.self_attn.v_proj: 8
+model.layers.14.mlp.gate_proj: 8
+model.layers.14.mlp.up_proj: 8
+model.layers.14.self_attn.k_proj: 8
+model.layers.14.self_attn.q_proj: 8
+model.layers.14.self_attn.v_proj: 8
+model.layers.15.mlp.gate_proj: 8
+model.layers.15.mlp.up_proj: 8
+model.layers.15.self_attn.k_proj: 8
+model.layers.15.self_attn.q_proj: 8
+model.layers.15.self_attn.v_proj: 8
+model.layers.16.mlp.gate_proj: 8
+model.layers.16.mlp.up_proj: 8
+model.layers.16.self_attn.k_proj: 8
+model.layers.16.self_attn.q_proj: 8
+model.layers.16.self_attn.v_proj: 8
+model.layers.17.mlp.gate_proj: 8
+model.layers.17.mlp.up_proj: 8
+model.layers.17.self_attn.k_proj: 8
+model.layers.17.self_attn.q_proj: 8
+model.layers.17.self_attn.v_proj: 8
+model.layers.18.mlp.gate_proj: 8
+model.layers.18.mlp.up_proj: 8
+model.layers.18.self_attn.k_proj: 8
+model.layers.18.self_attn.q_proj: 8
+model.layers.18.self_attn.v_proj: 8
+model.layers.19.mlp.gate_proj: 8
+model.layers.19.mlp.up_proj: 8
+model.layers.19.self_attn.k_proj: 8
+model.layers.19.self_attn.q_proj: 8
+model.layers.19.self_attn.v_proj: 8
+model.layers.20.mlp.gate_proj: 8
+model.layers.20.mlp.up_proj: 8
+model.layers.20.self_attn.k_proj: 8
+model.layers.20.self_attn.q_proj: 8
+model.layers.20.self_attn.v_proj: 8
+model.layers.21.mlp.gate_proj: 8
+model.layers.21.mlp.up_proj: 8
+model.layers.21.self_attn.k_proj: 8
+model.layers.21.self_attn.q_proj: 8
+model.layers.21.self_attn.v_proj: 8
+model.layers.22.mlp.gate_proj: 8
+model.layers.22.mlp.up_proj: 8
+model.layers.22.self_attn.k_proj: 8
+model.layers.22.self_attn.q_proj: 8
+model.layers.22.self_attn.v_proj: 8
+model.layers.23.mlp.gate_proj: 8
+model.layers.23.mlp.up_proj: 8
+model.layers.23.self_attn.k_proj: 8
+model.layers.23.self_attn.q_proj: 8
+model.layers.23.self_attn.v_proj: 8
+model.layers.24.mlp.gate_proj: 8
+model.layers.24.mlp.up_proj: 8
+model.layers.24.self_attn.k_proj: 8
+model.layers.24.self_attn.q_proj: 8
+model.layers.24.self_attn.v_proj: 8
+model.layers.25.mlp.gate_proj: 8
+model.layers.25.mlp.up_proj: 8
+model.layers.25.self_attn.k_proj: 8
+model.layers.25.self_attn.q_proj: 8
+model.layers.25.self_attn.v_proj: 8
+model.layers.26.mlp.gate_proj: 4
+model.layers.26.mlp.up_proj: 4
+model.layers.26.self_attn.k_proj: 8
+model.layers.26.self_attn.q_proj: 8
+model.layers.26.self_attn.v_proj: 8
+model.layers.27.mlp.gate_proj: 8
+model.layers.27.mlp.up_proj: 8
+model.layers.27.self_attn.k_proj: 8
+model.layers.27.self_attn.q_proj: 8
+model.layers.27.self_attn.v_proj: 8
+model.layers.28.mlp.gate_proj: 8
+model.layers.28.mlp.up_proj: 8
+model.layers.28.self_attn.k_proj: 8
+model.layers.28.self_attn.q_proj: 8
+model.layers.28.self_attn.v_proj: 8
+model.layers.29.mlp.gate_proj: 8
+model.layers.29.mlp.up_proj: 8
+model.layers.29.self_attn.k_proj: 8
+model.layers.29.self_attn.q_proj: 8
+model.layers.29.self_attn.v_proj: 8
+model.layers.30.mlp.gate_proj: 8
+model.layers.30.mlp.up_proj: 8
+model.layers.30.self_attn.k_proj: 8
+model.layers.30.self_attn.q_proj: 8
+model.layers.30.self_attn.v_proj: 8
+model.layers.31.mlp.gate_proj: 8
+model.layers.31.mlp.up_proj: 8
+model.layers.31.self_attn.k_proj: 8
+model.layers.31.self_attn.q_proj: 8
+model.layers.31.self_attn.v_proj: 8
+model.layers.32.mlp.gate_proj: 8
+model.layers.32.mlp.up_proj: 8
+model.layers.32.self_attn.k_proj: 8
+model.layers.32.self_attn.q_proj: 8
+model.layers.32.self_attn.v_proj: 8
+model.layers.33.mlp.gate_proj: 8
+model.layers.33.mlp.up_proj: 8
+model.layers.33.self_attn.k_proj: 8
+model.layers.33.self_attn.q_proj: 8
+model.layers.33.self_attn.v_proj: 8
+model.layers.34.mlp.gate_proj: 8
+model.layers.34.mlp.up_proj: 8
+model.layers.34.self_attn.k_proj: 8
+model.layers.34.self_attn.q_proj: 8
+model.layers.34.self_attn.v_proj: 8
+model.layers.35.mlp.gate_proj: 8
+model.layers.35.mlp.up_proj: 8
+model.layers.35.self_attn.k_proj: 8
+model.layers.35.self_attn.q_proj: 8
+model.layers.35.self_attn.v_proj: 8
+model.layers.1.mlp.down_proj: 4
+model.layers.8.mlp.down_proj: 8
+model.layers.13.self_attn.o_proj: 8
+model.layers.2.mlp.down_proj: 4
+model.layers.6.self_attn.o_proj: 8
+model.layers.9.mlp.down_proj: 8
+model.layers.5.self_attn.o_proj: 8
+model.layers.4.self_attn.o_proj: 8
+model.layers.5.mlp.down_proj: 8
+model.layers.3.self_attn.o_proj: 8
+model.layers.4.mlp.down_proj: 8
+model.layers.8.self_attn.o_proj: 8
+model.layers.0.self_attn.o_proj: 8
+model.layers.10.self_attn.o_proj: 8
+model.layers.2.self_attn.o_proj: 4
+model.layers.10.mlp.down_proj: 8
+model.layers.0.mlp.down_proj: 4
+model.layers.11.self_attn.o_proj: 8
+model.layers.11.mlp.down_proj: 8
+model.layers.12.self_attn.o_proj: 8
+model.layers.12.mlp.down_proj: 8
+model.layers.7.self_attn.o_proj: 8
+model.layers.1.self_attn.o_proj: 8
+model.layers.9.self_attn.o_proj: 8
+model.layers.3.mlp.down_proj: 4
+model.layers.7.mlp.down_proj: 8
+model.layers.6.mlp.down_proj: 8
+model.layers.25.self_attn.o_proj: 8
+model.layers.18.self_attn.o_proj: 8
+model.layers.28.mlp.down_proj: 8
+model.layers.19.self_attn.o_proj: 8
+model.layers.21.self_attn.o_proj: 8
+model.layers.16.self_attn.o_proj: 8
+model.layers.21.mlp.down_proj: 4
+model.layers.22.mlp.down_proj: 8
+model.layers.28.self_attn.o_proj: 8
+model.layers.35.mlp.down_proj: 8
+model.layers.23.mlp.down_proj: 8
+model.layers.15.mlp.down_proj: 4
+model.layers.20.self_attn.o_proj: 8
+model.layers.14.mlp.down_proj: 8
+model.layers.30.self_attn.o_proj: 8
+model.layers.30.mlp.down_proj: 8
+model.layers.33.self_attn.o_proj: 8
+model.layers.33.mlp.down_proj: 8
+model.layers.26.self_attn.o_proj: 8
+model.layers.29.mlp.down_proj: 4
+model.layers.15.self_attn.o_proj: 8
+model.layers.16.mlp.down_proj: 8
+model.layers.19.mlp.down_proj: 8
+model.layers.34.mlp.down_proj: 4
+model.layers.20.mlp.down_proj: 8
+model.layers.13.mlp.down_proj: 8
+model.layers.14.self_attn.o_proj: 8
+model.layers.31.self_attn.o_proj: 8
+model.layers.24.self_attn.o_proj: 8
+model.layers.18.mlp.down_proj: 4
+model.layers.23.self_attn.o_proj: 8
+model.layers.26.mlp.down_proj: 8
+model.layers.27.self_attn.o_proj: 8
+model.layers.17.self_attn.o_proj: 8
+model.layers.17.mlp.down_proj: 8
+model.layers.22.self_attn.o_proj: 8
+model.layers.24.mlp.down_proj: 8
+model.layers.27.mlp.down_proj: 8
+model.layers.31.mlp.down_proj: 8
+model.layers.25.mlp.down_proj: 8
+model.layers.32.self_attn.o_proj: 8
+model.layers.29.self_attn.o_proj: 8
+model.layers.32.mlp.down_proj: 8
+model.layers.35.self_attn.o_proj: 8
+model.layers.34.self_attn.o_proj: 8

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.60_4-8bit_grouped_seed1234/tokenizer_config.json

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/added_tokens.json

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/chat_template.jinja

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

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/quantization_config.txt

@@ -0,0 +1,460 @@
+# Model: Qwen/Qwen3-8B
+# Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4bit_asym_8bit_sym_g128/Qwen3-8B
+# Sensitivity method: shapley
+# Estimation method: permutation
+# Available bitwidths: [4, 8]
+# Bitwidth map: {4: 4.156, 5: 5.156, 6: 6.156, 7: 7.156, 8: 8.156}
+#
+# Layer groups: 144 groups (fused layers share bitwidth)
+#   block_0:mlp.gate_proj,mlp.up_proj.block_0:mlp.gate_proj,mlp.up_proj: group 0, 2 layers
+#   block_0:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 1, 3 layers
+#   block_10:mlp.gate_proj,mlp.up_proj.block_10:mlp.gate_proj,mlp.up_proj: group 20, 2 layers
+#   block_10:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 21, 3 layers
+#   block_11:mlp.gate_proj,mlp.up_proj.block_11:mlp.gate_proj,mlp.up_proj: group 22, 2 layers
+#   block_11:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 23, 3 layers
+#   block_12:mlp.gate_proj,mlp.up_proj.block_12:mlp.gate_proj,mlp.up_proj: group 24, 2 layers
+#   block_12:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 25, 3 layers
+#   block_13:mlp.gate_proj,mlp.up_proj.block_13:mlp.gate_proj,mlp.up_proj: group 26, 2 layers
+#   block_13:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 27, 3 layers
+#   block_14:mlp.gate_proj,mlp.up_proj.block_14:mlp.gate_proj,mlp.up_proj: group 28, 2 layers
+#   block_14:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 29, 3 layers
+#   block_15:mlp.gate_proj,mlp.up_proj.block_15:mlp.gate_proj,mlp.up_proj: group 30, 2 layers
+#   block_15:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 31, 3 layers
+#   block_16:mlp.gate_proj,mlp.up_proj.block_16:mlp.gate_proj,mlp.up_proj: group 32, 2 layers
+#   block_16:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 33, 3 layers
+#   block_17:mlp.gate_proj,mlp.up_proj.block_17:mlp.gate_proj,mlp.up_proj: group 34, 2 layers
+#   block_17:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 35, 3 layers
+#   block_18:mlp.gate_proj,mlp.up_proj.block_18:mlp.gate_proj,mlp.up_proj: group 36, 2 layers
+#   block_18:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 37, 3 layers
+#   block_19:mlp.gate_proj,mlp.up_proj.block_19:mlp.gate_proj,mlp.up_proj: group 38, 2 layers
+#   block_19:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 39, 3 layers
+#   block_1:mlp.gate_proj,mlp.up_proj.block_1:mlp.gate_proj,mlp.up_proj: group 2, 2 layers
+#   block_1:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 3, 3 layers
+#   block_20:mlp.gate_proj,mlp.up_proj.block_20:mlp.gate_proj,mlp.up_proj: group 40, 2 layers
+#   block_20:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 41, 3 layers
+#   block_21:mlp.gate_proj,mlp.up_proj.block_21:mlp.gate_proj,mlp.up_proj: group 42, 2 layers
+#   block_21:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 43, 3 layers
+#   block_22:mlp.gate_proj,mlp.up_proj.block_22:mlp.gate_proj,mlp.up_proj: group 44, 2 layers
+#   block_22:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 45, 3 layers
+#   block_23:mlp.gate_proj,mlp.up_proj.block_23:mlp.gate_proj,mlp.up_proj: group 46, 2 layers
+#   block_23:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 47, 3 layers
+#   block_24:mlp.gate_proj,mlp.up_proj.block_24:mlp.gate_proj,mlp.up_proj: group 48, 2 layers
+#   block_24:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 49, 3 layers
+#   block_25:mlp.gate_proj,mlp.up_proj.block_25:mlp.gate_proj,mlp.up_proj: group 50, 2 layers
+#   block_25:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 51, 3 layers
+#   block_26:mlp.gate_proj,mlp.up_proj.block_26:mlp.gate_proj,mlp.up_proj: group 52, 2 layers
+#   block_26:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 53, 3 layers
+#   block_27:mlp.gate_proj,mlp.up_proj.block_27:mlp.gate_proj,mlp.up_proj: group 54, 2 layers
+#   block_27:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 55, 3 layers
+#   block_28:mlp.gate_proj,mlp.up_proj.block_28:mlp.gate_proj,mlp.up_proj: group 56, 2 layers
+#   block_28:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 57, 3 layers
+#   block_29:mlp.gate_proj,mlp.up_proj.block_29:mlp.gate_proj,mlp.up_proj: group 58, 2 layers
+#   block_29:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 59, 3 layers
+#   block_2:mlp.gate_proj,mlp.up_proj.block_2:mlp.gate_proj,mlp.up_proj: group 4, 2 layers
+#   block_2:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 5, 3 layers
+#   block_30:mlp.gate_proj,mlp.up_proj.block_30:mlp.gate_proj,mlp.up_proj: group 60, 2 layers
+#   block_30:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 61, 3 layers
+#   block_31:mlp.gate_proj,mlp.up_proj.block_31:mlp.gate_proj,mlp.up_proj: group 62, 2 layers
+#   block_31:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 63, 3 layers
+#   block_32:mlp.gate_proj,mlp.up_proj.block_32:mlp.gate_proj,mlp.up_proj: group 64, 2 layers
+#   block_32:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 65, 3 layers
+#   block_33:mlp.gate_proj,mlp.up_proj.block_33:mlp.gate_proj,mlp.up_proj: group 66, 2 layers
+#   block_33:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 67, 3 layers
+#   block_34:mlp.gate_proj,mlp.up_proj.block_34:mlp.gate_proj,mlp.up_proj: group 68, 2 layers
+#   block_34:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 69, 3 layers
+#   block_35:mlp.gate_proj,mlp.up_proj.block_35:mlp.gate_proj,mlp.up_proj: group 70, 2 layers
+#   block_35:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 71, 3 layers
+#   block_3:mlp.gate_proj,mlp.up_proj.block_3:mlp.gate_proj,mlp.up_proj: group 6, 2 layers
+#   block_3:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 7, 3 layers
+#   block_4:mlp.gate_proj,mlp.up_proj.block_4:mlp.gate_proj,mlp.up_proj: group 8, 2 layers
+#   block_4:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 9, 3 layers
+#   block_5:mlp.gate_proj,mlp.up_proj.block_5:mlp.gate_proj,mlp.up_proj: group 10, 2 layers
+#   block_5:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 11, 3 layers
+#   block_6:mlp.gate_proj,mlp.up_proj.block_6:mlp.gate_proj,mlp.up_proj: group 12, 2 layers
+#   block_6:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 13, 3 layers
+#   block_7:mlp.gate_proj,mlp.up_proj.block_7:mlp.gate_proj,mlp.up_proj: group 14, 2 layers
+#   block_7:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 15, 3 layers
+#   block_8:mlp.gate_proj,mlp.up_proj.block_8:mlp.gate_proj,mlp.up_proj: group 16, 2 layers
+#   block_8:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 17, 3 layers
+#   block_9:mlp.gate_proj,mlp.up_proj.block_9:mlp.gate_proj,mlp.up_proj: group 18, 2 layers
+#   block_9:self_attn.k_proj,self_attn.q_proj,self_attn.v_proj: group 19, 3 layers
+#   Fused in model.layers.0:
+#     - self_attn.o_proj (group 84, 1 layers)
+#     - mlp.down_proj (group 88, 1 layers)
+#   Fused in model.layers.1:
+#     - mlp.down_proj (group 72, 1 layers)
+#     - self_attn.o_proj (group 94, 1 layers)
+#   Fused in model.layers.10:
+#     - self_attn.o_proj (group 85, 1 layers)
+#     - mlp.down_proj (group 87, 1 layers)
+#   Fused in model.layers.11:
+#     - self_attn.o_proj (group 89, 1 layers)
+#     - mlp.down_proj (group 90, 1 layers)
+#   Fused in model.layers.12:
+#     - self_attn.o_proj (group 91, 1 layers)
+#     - mlp.down_proj (group 92, 1 layers)
+#   Fused in model.layers.13:
+#     - self_attn.o_proj (group 74, 1 layers)
+#     - mlp.down_proj (group 124, 1 layers)
+#   Fused in model.layers.14:
+#     - mlp.down_proj (group 112, 1 layers)
+#     - self_attn.o_proj (group 125, 1 layers)
+#   Fused in model.layers.15:
+#     - mlp.down_proj (group 110, 1 layers)
+#     - self_attn.o_proj (group 119, 1 layers)
+#   Fused in model.layers.16:
+#     - self_attn.o_proj (group 104, 1 layers)
+#     - mlp.down_proj (group 120, 1 layers)
+#   Fused in model.layers.17:
+#     - self_attn.o_proj (group 132, 1 layers)
+#     - mlp.down_proj (group 133, 1 layers)
+#   Fused in model.layers.18:
+#     - self_attn.o_proj (group 100, 1 layers)
+#     - mlp.down_proj (group 128, 1 layers)
+#   Fused in model.layers.19:
+#     - self_attn.o_proj (group 102, 1 layers)
+#     - mlp.down_proj (group 121, 1 layers)
+#   Fused in model.layers.2:
+#     - mlp.down_proj (group 75, 1 layers)
+#     - self_attn.o_proj (group 86, 1 layers)
+#   Fused in model.layers.20:
+#     - self_attn.o_proj (group 111, 1 layers)
+#     - mlp.down_proj (group 123, 1 layers)
+#   Fused in model.layers.21:
+#     - self_attn.o_proj (group 103, 1 layers)
+#     - mlp.down_proj (group 105, 1 layers)
+#   Fused in model.layers.22:
+#     - mlp.down_proj (group 106, 1 layers)
+#     - self_attn.o_proj (group 134, 1 layers)
+#   Fused in model.layers.23:
+#     - mlp.down_proj (group 109, 1 layers)
+#     - self_attn.o_proj (group 129, 1 layers)
+#   Fused in model.layers.24:
+#     - self_attn.o_proj (group 127, 1 layers)
+#     - mlp.down_proj (group 135, 1 layers)
+#   Fused in model.layers.25:
+#     - self_attn.o_proj (group 99, 1 layers)
+#     - mlp.down_proj (group 138, 1 layers)
+#   Fused in model.layers.26:
+#     - self_attn.o_proj (group 117, 1 layers)
+#     - mlp.down_proj (group 130, 1 layers)
+#   Fused in model.layers.27:
+#     - self_attn.o_proj (group 131, 1 layers)
+#     - mlp.down_proj (group 136, 1 layers)
+#   Fused in model.layers.28:
+#     - mlp.down_proj (group 101, 1 layers)
+#     - self_attn.o_proj (group 107, 1 layers)
+#   Fused in model.layers.29:
+#     - mlp.down_proj (group 118, 1 layers)
+#     - self_attn.o_proj (group 140, 1 layers)
+#   Fused in model.layers.3:
+#     - self_attn.o_proj (group 81, 1 layers)
+#     - mlp.down_proj (group 96, 1 layers)
+#   Fused in model.layers.30:
+#     - self_attn.o_proj (group 113, 1 layers)
+#     - mlp.down_proj (group 114, 1 layers)
+#   Fused in model.layers.31:
+#     - self_attn.o_proj (group 126, 1 layers)
+#     - mlp.down_proj (group 137, 1 layers)
+#   Fused in model.layers.32:
+#     - self_attn.o_proj (group 139, 1 layers)
+#     - mlp.down_proj (group 141, 1 layers)
+#   Fused in model.layers.33:
+#     - self_attn.o_proj (group 115, 1 layers)
+#     - mlp.down_proj (group 116, 1 layers)
+#   Fused in model.layers.34:
+#     - mlp.down_proj (group 122, 1 layers)
+#     - self_attn.o_proj (group 143, 1 layers)
+#   Fused in model.layers.35:
+#     - mlp.down_proj (group 108, 1 layers)
+#     - self_attn.o_proj (group 142, 1 layers)
+#   Fused in model.layers.4:
+#     - self_attn.o_proj (group 79, 1 layers)
+#     - mlp.down_proj (group 82, 1 layers)
+#   Fused in model.layers.5:
+#     - self_attn.o_proj (group 78, 1 layers)
+#     - mlp.down_proj (group 80, 1 layers)
+#   Fused in model.layers.6:
+#     - self_attn.o_proj (group 76, 1 layers)
+#     - mlp.down_proj (group 98, 1 layers)
+#   Fused in model.layers.7:
+#     - self_attn.o_proj (group 93, 1 layers)
+#     - mlp.down_proj (group 97, 1 layers)
+#   Fused in model.layers.8:
+#     - mlp.down_proj (group 73, 1 layers)
+#     - self_attn.o_proj (group 83, 1 layers)
+#   Fused in model.layers.9:
+#     - mlp.down_proj (group 77, 1 layers)
+#     - self_attn.o_proj (group 95, 1 layers)
+#
+# Mode: binary_search_constraint (measured)
+# Constraint max_kl: 0.01
+# Constraint min_eap: 0.99
+# Weights: nll=0.0, kl=0.0, eap=1.0
+#
+# Average bitwidth: 7.6053
+# Total params: 6945767424
+# Total bits: 52824473862
+# Final KL: 0.001590
+# Final EAP: 0.990007
+# Final ETL: 0.009993
+# Satisfies constraints: True
+# Solver calls: 9
+# Evaluations: 9
+#
+# Bitwidth distribution:
+#   8-bit: 233 layers (92.5%)
+#   4-bit: 19 layers (7.5%)
+#
+model.layers.0.mlp.gate_proj: 4
+model.layers.0.mlp.up_proj: 4
+model.layers.0.self_attn.k_proj: 8
+model.layers.0.self_attn.q_proj: 8
+model.layers.0.self_attn.v_proj: 8
+model.layers.1.mlp.gate_proj: 4
+model.layers.1.mlp.up_proj: 4
+model.layers.1.self_attn.k_proj: 8
+model.layers.1.self_attn.q_proj: 8
+model.layers.1.self_attn.v_proj: 8
+model.layers.2.mlp.gate_proj: 4
+model.layers.2.mlp.up_proj: 4
+model.layers.2.self_attn.k_proj: 8
+model.layers.2.self_attn.q_proj: 8
+model.layers.2.self_attn.v_proj: 8
+model.layers.3.mlp.gate_proj: 4
+model.layers.3.mlp.up_proj: 4
+model.layers.3.self_attn.k_proj: 8
+model.layers.3.self_attn.q_proj: 8
+model.layers.3.self_attn.v_proj: 8
+model.layers.4.mlp.gate_proj: 8
+model.layers.4.mlp.up_proj: 8
+model.layers.4.self_attn.k_proj: 8
+model.layers.4.self_attn.q_proj: 8
+model.layers.4.self_attn.v_proj: 8
+model.layers.5.mlp.gate_proj: 8
+model.layers.5.mlp.up_proj: 8
+model.layers.5.self_attn.k_proj: 8
+model.layers.5.self_attn.q_proj: 8
+model.layers.5.self_attn.v_proj: 8
+model.layers.6.mlp.gate_proj: 8
+model.layers.6.mlp.up_proj: 8
+model.layers.6.self_attn.k_proj: 8
+model.layers.6.self_attn.q_proj: 8
+model.layers.6.self_attn.v_proj: 8
+model.layers.7.mlp.gate_proj: 8
+model.layers.7.mlp.up_proj: 8
+model.layers.7.self_attn.k_proj: 8
+model.layers.7.self_attn.q_proj: 8
+model.layers.7.self_attn.v_proj: 8
+model.layers.8.mlp.gate_proj: 8
+model.layers.8.mlp.up_proj: 8
+model.layers.8.self_attn.k_proj: 8
+model.layers.8.self_attn.q_proj: 8
+model.layers.8.self_attn.v_proj: 8
+model.layers.9.mlp.gate_proj: 8
+model.layers.9.mlp.up_proj: 8
+model.layers.9.self_attn.k_proj: 8
+model.layers.9.self_attn.q_proj: 8
+model.layers.9.self_attn.v_proj: 8
+model.layers.10.mlp.gate_proj: 8
+model.layers.10.mlp.up_proj: 8
+model.layers.10.self_attn.k_proj: 8
+model.layers.10.self_attn.q_proj: 8
+model.layers.10.self_attn.v_proj: 8
+model.layers.11.mlp.gate_proj: 8
+model.layers.11.mlp.up_proj: 8
+model.layers.11.self_attn.k_proj: 8
+model.layers.11.self_attn.q_proj: 8
+model.layers.11.self_attn.v_proj: 8
+model.layers.12.mlp.gate_proj: 8
+model.layers.12.mlp.up_proj: 8
+model.layers.12.self_attn.k_proj: 8
+model.layers.12.self_attn.q_proj: 8
+model.layers.12.self_attn.v_proj: 8
+model.layers.13.mlp.gate_proj: 8
+model.layers.13.mlp.up_proj: 8
+model.layers.13.self_attn.k_proj: 8
+model.layers.13.self_attn.q_proj: 8
+model.layers.13.self_attn.v_proj: 8
+model.layers.14.mlp.gate_proj: 8
+model.layers.14.mlp.up_proj: 8
+model.layers.14.self_attn.k_proj: 8
+model.layers.14.self_attn.q_proj: 8
+model.layers.14.self_attn.v_proj: 8
+model.layers.15.mlp.gate_proj: 8
+model.layers.15.mlp.up_proj: 8
+model.layers.15.self_attn.k_proj: 8
+model.layers.15.self_attn.q_proj: 8
+model.layers.15.self_attn.v_proj: 8
+model.layers.16.mlp.gate_proj: 8
+model.layers.16.mlp.up_proj: 8
+model.layers.16.self_attn.k_proj: 8
+model.layers.16.self_attn.q_proj: 8
+model.layers.16.self_attn.v_proj: 8
+model.layers.17.mlp.gate_proj: 8
+model.layers.17.mlp.up_proj: 8
+model.layers.17.self_attn.k_proj: 8
+model.layers.17.self_attn.q_proj: 8
+model.layers.17.self_attn.v_proj: 8
+model.layers.18.mlp.gate_proj: 8
+model.layers.18.mlp.up_proj: 8
+model.layers.18.self_attn.k_proj: 8
+model.layers.18.self_attn.q_proj: 8
+model.layers.18.self_attn.v_proj: 8
+model.layers.19.mlp.gate_proj: 8
+model.layers.19.mlp.up_proj: 8
+model.layers.19.self_attn.k_proj: 8
+model.layers.19.self_attn.q_proj: 8
+model.layers.19.self_attn.v_proj: 8
+model.layers.20.mlp.gate_proj: 8
+model.layers.20.mlp.up_proj: 8
+model.layers.20.self_attn.k_proj: 8
+model.layers.20.self_attn.q_proj: 8
+model.layers.20.self_attn.v_proj: 8
+model.layers.21.mlp.gate_proj: 8
+model.layers.21.mlp.up_proj: 8
+model.layers.21.self_attn.k_proj: 8
+model.layers.21.self_attn.q_proj: 8
+model.layers.21.self_attn.v_proj: 8
+model.layers.22.mlp.gate_proj: 8
+model.layers.22.mlp.up_proj: 8
+model.layers.22.self_attn.k_proj: 8
+model.layers.22.self_attn.q_proj: 8
+model.layers.22.self_attn.v_proj: 8
+model.layers.23.mlp.gate_proj: 8
+model.layers.23.mlp.up_proj: 8
+model.layers.23.self_attn.k_proj: 8
+model.layers.23.self_attn.q_proj: 8
+model.layers.23.self_attn.v_proj: 8
+model.layers.24.mlp.gate_proj: 8
+model.layers.24.mlp.up_proj: 8
+model.layers.24.self_attn.k_proj: 8
+model.layers.24.self_attn.q_proj: 8
+model.layers.24.self_attn.v_proj: 8
+model.layers.25.mlp.gate_proj: 8
+model.layers.25.mlp.up_proj: 8
+model.layers.25.self_attn.k_proj: 8
+model.layers.25.self_attn.q_proj: 8
+model.layers.25.self_attn.v_proj: 8
+model.layers.26.mlp.gate_proj: 4
+model.layers.26.mlp.up_proj: 4
+model.layers.26.self_attn.k_proj: 8
+model.layers.26.self_attn.q_proj: 8
+model.layers.26.self_attn.v_proj: 8
+model.layers.27.mlp.gate_proj: 8
+model.layers.27.mlp.up_proj: 8
+model.layers.27.self_attn.k_proj: 8
+model.layers.27.self_attn.q_proj: 8
+model.layers.27.self_attn.v_proj: 8
+model.layers.28.mlp.gate_proj: 8
+model.layers.28.mlp.up_proj: 8
+model.layers.28.self_attn.k_proj: 8
+model.layers.28.self_attn.q_proj: 8
+model.layers.28.self_attn.v_proj: 8
+model.layers.29.mlp.gate_proj: 8
+model.layers.29.mlp.up_proj: 8
+model.layers.29.self_attn.k_proj: 8
+model.layers.29.self_attn.q_proj: 8
+model.layers.29.self_attn.v_proj: 8
+model.layers.30.mlp.gate_proj: 8
+model.layers.30.mlp.up_proj: 8
+model.layers.30.self_attn.k_proj: 8
+model.layers.30.self_attn.q_proj: 8
+model.layers.30.self_attn.v_proj: 8
+model.layers.31.mlp.gate_proj: 8
+model.layers.31.mlp.up_proj: 8
+model.layers.31.self_attn.k_proj: 8
+model.layers.31.self_attn.q_proj: 8
+model.layers.31.self_attn.v_proj: 8
+model.layers.32.mlp.gate_proj: 8
+model.layers.32.mlp.up_proj: 8
+model.layers.32.self_attn.k_proj: 8
+model.layers.32.self_attn.q_proj: 8
+model.layers.32.self_attn.v_proj: 8
+model.layers.33.mlp.gate_proj: 8
+model.layers.33.mlp.up_proj: 8
+model.layers.33.self_attn.k_proj: 8
+model.layers.33.self_attn.q_proj: 8
+model.layers.33.self_attn.v_proj: 8
+model.layers.34.mlp.gate_proj: 8
+model.layers.34.mlp.up_proj: 8
+model.layers.34.self_attn.k_proj: 8
+model.layers.34.self_attn.q_proj: 8
+model.layers.34.self_attn.v_proj: 8
+model.layers.35.mlp.gate_proj: 8
+model.layers.35.mlp.up_proj: 8
+model.layers.35.self_attn.k_proj: 8
+model.layers.35.self_attn.q_proj: 8
+model.layers.35.self_attn.v_proj: 8
+model.layers.1.mlp.down_proj: 4
+model.layers.8.mlp.down_proj: 8
+model.layers.13.self_attn.o_proj: 8
+model.layers.2.mlp.down_proj: 4
+model.layers.6.self_attn.o_proj: 8
+model.layers.9.mlp.down_proj: 8
+model.layers.5.self_attn.o_proj: 8
+model.layers.4.self_attn.o_proj: 8
+model.layers.5.mlp.down_proj: 8
+model.layers.3.self_attn.o_proj: 8
+model.layers.4.mlp.down_proj: 8
+model.layers.8.self_attn.o_proj: 8
+model.layers.0.self_attn.o_proj: 8
+model.layers.10.self_attn.o_proj: 8
+model.layers.2.self_attn.o_proj: 8
+model.layers.10.mlp.down_proj: 8
+model.layers.0.mlp.down_proj: 4
+model.layers.11.self_attn.o_proj: 8
+model.layers.11.mlp.down_proj: 8
+model.layers.12.self_attn.o_proj: 8
+model.layers.12.mlp.down_proj: 8
+model.layers.7.self_attn.o_proj: 8
+model.layers.1.self_attn.o_proj: 8
+model.layers.9.self_attn.o_proj: 8
+model.layers.3.mlp.down_proj: 4
+model.layers.7.mlp.down_proj: 8
+model.layers.6.mlp.down_proj: 8
+model.layers.25.self_attn.o_proj: 8
+model.layers.18.self_attn.o_proj: 8
+model.layers.28.mlp.down_proj: 8
+model.layers.19.self_attn.o_proj: 8
+model.layers.21.self_attn.o_proj: 8
+model.layers.16.self_attn.o_proj: 8
+model.layers.21.mlp.down_proj: 4
+model.layers.22.mlp.down_proj: 8
+model.layers.28.self_attn.o_proj: 8
+model.layers.35.mlp.down_proj: 8
+model.layers.23.mlp.down_proj: 8
+model.layers.15.mlp.down_proj: 4
+model.layers.20.self_attn.o_proj: 8
+model.layers.14.mlp.down_proj: 8
+model.layers.30.self_attn.o_proj: 8
+model.layers.30.mlp.down_proj: 8
+model.layers.33.self_attn.o_proj: 8
+model.layers.33.mlp.down_proj: 8
+model.layers.26.self_attn.o_proj: 8
+model.layers.29.mlp.down_proj: 4
+model.layers.15.self_attn.o_proj: 8
+model.layers.16.mlp.down_proj: 8
+model.layers.19.mlp.down_proj: 8
+model.layers.34.mlp.down_proj: 4
+model.layers.20.mlp.down_proj: 8
+model.layers.13.mlp.down_proj: 8
+model.layers.14.self_attn.o_proj: 8
+model.layers.31.self_attn.o_proj: 8
+model.layers.24.self_attn.o_proj: 8
+model.layers.18.mlp.down_proj: 4
+model.layers.23.self_attn.o_proj: 8
+model.layers.26.mlp.down_proj: 8
+model.layers.27.self_attn.o_proj: 8
+model.layers.17.self_attn.o_proj: 8
+model.layers.17.mlp.down_proj: 8
+model.layers.22.self_attn.o_proj: 8
+model.layers.24.mlp.down_proj: 8
+model.layers.27.mlp.down_proj: 8
+model.layers.31.mlp.down_proj: 8
+model.layers.25.mlp.down_proj: 8
+model.layers.32.self_attn.o_proj: 8
+model.layers.29.self_attn.o_proj: 8
+model.layers.32.mlp.down_proj: 8
+model.layers.35.self_attn.o_proj: 8
+model.layers.34.self_attn.o_proj: 8

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

4bit-asym_8bit-sym/Qwen3-8B/ll_bsearch_kl0.01_eap0.99_sha_bw7.61_4-8bit_grouped_seed42/tokenizer_config.json

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