Model save

README.md

@@ -1,10 +1,9 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: Qwen/Qwen2.5-7B-Instruct
+base_model: Qwen/Qwen3-8B
 tags:
 - llama-factory
-- full
 - generated_from_trainer
 model-index:
 - name: a1_math_formulas
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # a1_math_formulas
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/a1_math_formulas dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on an unknown dataset.
 
 ## Model description
 
@@ -41,10 +40,10 @@ The following hyperparameters were used during training:
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 16
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - total_eval_batch_size: 128
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5.0

added_tokens.json

@@ -1,6 +1,10 @@
 {
+  "</think>": 151668,
   "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
   "<tool_call>": 151657,
+  "<tool_response>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

chat_template.jinja

@@ -1,48 +1,80 @@
 {%- if tools %}
     {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
     {%- endif %}
-    {{- "\n\n# 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>" }}
+    {{- "# 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' }}
-    {%- else %}
-        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- 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.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- 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" %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
+        {%- 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 %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
+        {%- 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 %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- '}\n</tool_call>' }}
-        {%- endfor %}
+        {%- 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.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}
         {%- endif %}
         {{- '\n<tool_response>\n' }}
-        {{- message.content }}
+        {{- content }}
         {{- '\n</tool_response>' }}
         {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
             {{- '<|im_end|>\n' }}
@@ -51,4 +83,7 @@
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
-{%- endif %}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -1,14 +1,16 @@
 {
   "architectures": [
-    "Qwen2ForCausalLM"
+    "Qwen3ForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
+  "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 3584,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 18944,
+  "intermediate_size": 12288,
   "layer_types": [
     "full_attention",
     "full_attention",
@@ -37,22 +39,30 @@
     "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": 32768,
-  "max_window_layers": 28,
-  "model_type": "qwen2",
-  "num_attention_heads": 28,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
+  "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": 1000000.0,
+  "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.55.0",
   "use_cache": false,
   "use_sliding_window": false,
-  "vocab_size": 152064
+  "vocab_size": 151936
 }

generation_config.json

@@ -6,9 +6,8 @@
     151643
   ],
   "pad_token_id": 151643,
-  "repetition_penalty": 1.05,
-  "temperature": 0.7,
+  "temperature": 0.6,
   "top_k": 20,
-  "top_p": 0.8,
+  "top_p": 0.95,
   "transformers_version": "4.55.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594d66fb48a47d0cdeb937cd253d526b471c36f52910b4522880edb09b15ff84
-size 4877660776
+oid sha256:a3cdfac936576f5ffb8e0c5a69ab6f68cfefaa7c56d2b889bda2c7ac7af2860f
+size 4902257696

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:785820cad34feabf8f6ec6eef2207509732f3408c9306ed471747279b908fe91
-size 4932751008
+oid sha256:b992180109661e9722a732794766d81ffca9f64808ec6027ba66f6597ec07a77
+size 4915960368

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e0e5f8454dcc9d8e6ffebaca099fb547a7bba78d0869364511f2f76e559c8b
-size 4330865200
+oid sha256:51e38ecdabbc56b65c50a2b660ff31043011de76f044196f856de072a83424d1
+size 4983068496

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a235ff96caac8a9b8bd1bf6b2fbb6f7a101dd2a9a6e940ad19bd75111b53086
-size 1089994880
+oid sha256:40b4556320a54cbea19b02840c8629a0b65dc19627d92083e7f4551d9ba5d862
+size 1580230264

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 333312,
-    "total_size": 15231233024
+    "total_parameters": 308224,
+    "total_size": 16381470720
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",
@@ -11,337 +11,397 @@
     "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-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_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-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_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00002-of-00004.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-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_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.norm.weight": "model-00003-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"
   }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -177,6 +177,38 @@
       "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": [
@@ -199,7 +231,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 16384,
+  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
   "split_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d00beb6c7822b727035828821276d6a1e137aa38169392711d52a5c616ae8f
+oid sha256:02c4ae25514279ab1d2827dc57eb68aed0cf9a9aa4b79d637acebc16b390765d
 size 8465