Upload fine-tuned model

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-epoch-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- 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.' }}
+    {%- 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>" }}
+    {%- 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' }}
+    {%- endif %}
+{%- endif %}
+{%- 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' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}

checkpoint-epoch-1/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

checkpoint-epoch-1/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- 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.' }}
+    {%- 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>" }}
+    {%- 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' }}
+    {%- endif %}
+{%- endif %}
+{%- 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' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}

checkpoint-epoch-1/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-epoch-1/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.52.4"
+}

checkpoint-epoch-1/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece005a0b347ec0097dd97e49f6420d0e1a7da7fb8e2352072e226453e90dd07
+size 4996670464

checkpoint-epoch-1/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e9e88070bddad6e6245d3c532fe3058406fc5c498fa36bacdce2e67e4db6ff
+size 1178224960

checkpoint-epoch-1/model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+  "metadata": {
+    "total_size": 6174857216
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-epoch-1/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-epoch-1/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-epoch-1/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.52.4"
+}

logs/metrics.csv

@@ -0,0 +1,270 @@
+timestamp,epoch,step,train_loss,train_perplexity,eval_loss,eval_perplexity,learning_rate,grad_norm
+2025-06-04T15:48:13.078266,1,10,10,4.671072721481323,106.81226080494424,,,3.7313432835820895e-07,128.40884399414062
+2025-06-04T15:48:16.975402,1,20,20,1.949156641960144,7.022762379292836,,,7.462686567164179e-07,165.83786010742188
+2025-06-04T15:48:20.859988,1,30,30,0.3046633452177048,1.3561683655800802,,,1.119402985074627e-06,2.2541606426239014
+2025-06-04T15:48:24.742224,1,40,40,0.3191399648785591,1.3759438952493854,,,1.4925373134328358e-06,1.6307425498962402
+2025-06-04T15:48:45.625340,1,50,50,0.2649899423122406,1.303417866342524,,,1.865671641791045e-06,1.4340673685073853
+2025-06-04T15:48:49.505420,1,60,60,0.3226696774363518,1.380809163142544,,,2.238805970149254e-06,1.825088620185852
+2025-06-04T15:48:53.380713,1,70,70,0.16062812507152557,1.1742482141392039,,,2.6119402985074627e-06,1.1731597185134888
+2025-06-04T15:48:57.241477,1,80,80,0.1917380765080452,1.2113531935510409,,,2.9850746268656716e-06,1.4646199941635132
+2025-06-04T15:49:01.098674,1,90,90,0.19584764540195465,1.2163415759848903,,,3.3582089552238813e-06,1.5290420055389404
+2025-06-04T15:49:21.995753,1,100,100,0.2458140328526497,1.2786617623495191,,,3.73134328358209e-06,1.8633289337158203
+2025-06-04T15:49:25.878003,1,110,110,0.1814446747303009,1.1989482027420864,,,4.104477611940299e-06,1.3574203252792358
+2025-06-04T15:49:29.741404,1,120,120,0.21781329810619354,1.2433549092313039,,,4.477611940298508e-06,1.5201458930969238
+2025-06-04T15:49:33.621621,1,130,130,0.16430367529392242,1.1785721640033482,,,4.850746268656717e-06,1.3497518301010132
+2025-06-04T15:49:37.502736,1,140,140,0.17524391412734985,1.191536813832685,,,5.2238805970149255e-06,1.2528648376464844
+2025-06-04T15:49:58.449942,1,150,150,0.20567508041858673,1.2283540228730032,,,5.597014925373134e-06,1.3659957647323608
+2025-06-04T15:50:02.329556,1,160,160,0.15652210637927055,1.169436614042621,,,5.970149253731343e-06,1.2447582483291626
+2025-06-04T15:50:06.215832,1,170,170,0.23489902913570404,1.2647810562489856,,,6.343283582089553e-06,1.4126760959625244
+2025-06-04T15:50:10.079518,1,180,180,0.19649717211723328,1.217131878967062,,,6.7164179104477625e-06,1.2898818254470825
+2025-06-04T15:50:13.968221,1,190,190,0.1695742830634117,1.184800354364207,,,7.089552238805971e-06,1.2228553295135498
+2025-06-04T15:50:34.972471,1,200,200,0.09251426719129086,1.0969287915415644,,,7.46268656716418e-06,0.8676640391349792
+2025-06-04T15:50:38.854436,1,210,210,0.19059253484010696,1.2099663324984606,,,7.835820895522389e-06,1.3530491590499878
+2025-06-04T15:50:42.740946,1,220,220,0.1853446662425995,1.2036332203827504,,,8.208955223880599e-06,1.1952266693115234
+2025-06-04T15:50:46.624457,1,230,230,0.17687048763036728,1.1934765131460265,,,8.582089552238807e-06,1.252812385559082
+2025-06-04T15:50:50.515276,1,240,240,0.18703439086675644,1.2056687483302178,,,8.955223880597016e-06,1.1214816570281982
+2025-06-04T15:51:11.600965,1,250,250,0.14947571232914925,1.1612252670124277,,,9.328358208955226e-06,1.126630425453186
+2025-06-04T15:51:15.475835,1,260,260,0.1320449560880661,1.1411596201864647,,,9.701492537313434e-06,1.0430641174316406
+2025-06-04T15:51:19.374491,1,270,270,0.17876822501420975,1.1957435685993218,,,9.999983035350438e-06,1.14077627658844
+2025-06-04T15:51:23.241027,1,280,280,0.1122770607471466,1.1188227995878834,,,9.999389284703265e-06,0.9659624099731445
+2025-06-04T15:51:27.128086,1,290,290,0.07831090688705444,1.0814588394081597,,,9.997947416694233e-06,0.7408416271209717
+2025-06-04T15:51:48.202371,1,300,300,0.21869849413633347,1.244456009333831,,,9.995657675927874e-06,1.3368358612060547
+2025-06-04T15:51:52.092307,1,310,310,0.196963831782341,1.2176999978708714,,,9.992520450845415e-06,1.2888882160186768
+2025-06-04T15:51:55.962190,1,320,320,0.12523503229022026,1.133414810843023,,,9.988536273658876e-06,0.9675649404525757
+2025-06-04T15:51:59.850182,1,330,330,0.10732617415487766,1.1132973240779556,,,9.983705820260776e-06,0.8802552819252014
+2025-06-04T15:52:03.739457,1,340,340,0.11835997551679611,1.1256492446125033,,,9.978029910109491e-06,1.1237599849700928
+2025-06-04T15:52:24.820733,1,350,350,0.12786667421460152,1.1364014809764293,,,9.971509506090216e-06,0.9043460488319397
+2025-06-04T15:52:28.712642,1,360,360,0.1164625994861126,1.123515489624736,,,9.964145714351633e-06,1.0198386907577515
+2025-06-04T15:52:32.587060,1,370,370,0.2362208068370819,1.2664539209803558,,,9.955939784118246e-06,1.3103463649749756
+2025-06-04T15:52:36.459376,1,380,380,0.1618729755282402,1.1757108877809606,,,9.946893107478473e-06,1.0293731689453125
+2025-06-04T15:52:40.338426,1,390,390,0.0980859249830246,1.1030575612388553,,,9.937007219148473e-06,0.7921751737594604
+2025-06-04T15:53:01.448046,1,400,400,0.20105715841054916,1.2226946571092294,,,9.926283796211796e-06,1.0909723043441772
+2025-06-04T15:53:05.335319,1,410,410,0.22509319335222244,1.2524394297822314,,,9.914724657834875e-06,1.2618776559829712
+2025-06-04T15:53:09.208929,1,420,420,0.28387679159641266,1.328269266734722,,,9.902331764958412e-06,1.3388011455535889
+2025-06-04T15:53:13.287854,1,430,430,0.16169708222150803,1.1755041062914209,,,9.889107219964726e-06,1.1124091148376465
+2025-06-04T15:53:17.184992,1,440,440,0.11832941696047783,1.1256148469222418,,,9.87505326632108e-06,0.9476931691169739
+2025-06-04T15:53:38.261983,1,450,450,0.1749972589313984,1.1912429513292322,,,9.8601722881991e-06,1.1345462799072266
+2025-06-04T15:53:42.134995,1,460,460,0.08550283685326576,1.0892646514236664,,,9.844466810070319e-06,0.6836742758750916
+2025-06-04T15:53:46.024181,1,470,470,0.12165988981723785,1.1293699262409955,,,9.827939496277901e-06,0.9041603803634644
+2025-06-04T15:53:49.913415,1,480,480,0.14826585724949837,1.159821202253221,,,9.810593150584658e-06,1.0981465578079224
+2025-06-04T15:53:53.803995,1,490,490,0.17808087170124054,1.194921952698537,,,9.792430715697412e-06,1.0859241485595703
+2025-06-04T15:54:14.951227,1,500,500,0.1023472435772419,1.1077680702968618,,,9.77345527276778e-06,0.8103573322296143
+2025-06-04T15:54:18.850223,1,510,510,0.16731278225779533,1.1821239548887807,,,9.753670040869466e-06,1.0387943983078003
+2025-06-04T15:54:22.742237,1,520,520,0.12773668766021729,1.1362537736637104,,,9.733078376452172e-06,0.8454576134681702
+2025-06-04T15:54:26.637383,1,530,530,0.18833771720528603,1.2072411526208404,,,9.711683772772197e-06,1.190935730934143
+2025-06-04T15:54:30.534207,1,540,540,0.19391634687781334,1.2139947242594389,,,9.689489859299823e-06,1.0974748134613037
+2025-06-04T15:54:51.675683,1,550,550,0.14488542079925537,1.1559071197662123,,,9.666500401103595e-06,0.9678713083267212
+2025-06-04T15:54:55.569836,1,560,560,0.16025637090206146,1.173811763600792,,,9.642719298211602e-06,1.06119966506958
+2025-06-04T15:54:59.460516,1,570,570,0.1826080083847046,1.2003437911463095,,,9.618150584949858e-06,1.219964623451233
+2025-06-04T15:55:03.348911,1,580,580,0.14983021840453148,1.1616370014013302,,,9.592798429257899e-06,0.9647617340087891
+2025-06-04T15:55:07.234371,1,590,590,0.06683030910789967,1.0691140438653002,,,9.56666713198173e-06,0.6835302114486694
+2025-06-04T15:55:28.328386,1,600,600,0.14879680424928665,1.1604371693493187,,,9.539761126144193e-06,0.9380856156349182
+2025-06-04T15:55:32.201388,1,610,610,0.20094577968120575,1.222558482515563,,,9.512084976192944e-06,1.6561542749404907
+2025-06-04T15:55:36.097604,1,620,620,0.12645913287997246,1.1348030740949924,,,9.483643377226107e-06,0.8381012082099915
+2025-06-04T15:55:39.971556,1,630,630,0.15692076086997986,1.169902908139351,,,9.4544411541958e-06,1.0088982582092285
+2025-06-04T15:55:43.864524,1,640,640,0.152855534106493,1.1651566413882393,,,9.424483261089584e-06,0.9556991457939148
+2025-06-04T15:56:04.918510,1,650,650,0.10202617943286896,1.1074124627786746,,,9.39377478009007e-06,0.7985841631889343
+2025-06-04T15:56:08.805577,1,660,660,0.10977356135845184,1.1160253305851233,,,9.36232092071274e-06,0.7995733022689819
+2025-06-04T15:56:12.690636,1,670,670,0.08872723206877708,1.092782539637229,,,9.330127018922195e-06,0.7211840748786926
+2025-06-04T15:56:16.581263,1,680,680,0.1401810497045517,1.1504820744422115,,,9.297198536226927e-06,0.8916677236557007
+2025-06-04T15:56:20.469276,1,690,690,0.1811549961566925,1.1986009434361042,,,9.26354105875282e-06,1.0837889909744263
+2025-06-04T15:56:41.507497,1,700,700,0.17966965585947037,1.1968219346982898,,,9.229160296295488e-06,1.1415470838546753
+2025-06-04T15:56:45.399329,1,710,710,0.08297113329172134,1.0865104441155142,,,9.194062081351638e-06,0.6988579034805298
+2025-06-04T15:56:49.283621,1,720,720,0.21730352938175201,1.242721247309434,,,9.158252368129628e-06,1.173891305923462
+2025-06-04T15:56:53.169881,1,730,730,0.11370521038770676,1.1204217874921896,,,9.121737231539369e-06,0.9612295627593994
+2025-06-04T15:56:57.061155,1,740,740,0.1307085007429123,1.139635529978495,,,9.084522866161747e-06,0.8802459836006165
+2025-06-04T15:57:18.033686,1,750,750,0.21306980401277542,1.2374710286723147,,,9.046615585197753e-06,1.119827389717102
+2025-06-04T15:57:21.917915,1,760,760,0.10635868832468987,1.1122207455633288,,,9.008021819397488e-06,0.7633558511734009
+2025-06-04T15:57:25.803713,1,770,770,0.09661010652780533,1.1014308491938922,,,8.968748115969211e-06,0.8787773251533508
+2025-06-04T15:57:29.683554,1,780,780,0.14135663956403732,1.1518353648038036,,,8.928801137468654e-06,0.9087620377540588
+2025-06-04T15:57:33.561708,1,790,790,0.09599808976054192,1.1007569612825894,,,8.888187660668762e-06,0.8097870945930481
+2025-06-04T15:57:54.498816,1,800,800,0.13304192572832108,1.1422978889979176,,,8.846914575410035e-06,0.8932214975357056
+2025-06-04T15:57:58.352666,1,810,810,0.17763880267739296,1.1943938314589546,,,8.804988883431728e-06,1.072876214981079
+2025-06-04T15:58:02.235000,1,820,820,0.09748945012688637,1.1023998113238476,,,8.762417697184034e-06,0.8411881923675537
+2025-06-04T15:58:06.111317,1,830,830,0.13653943687677383,1.1463000833795116,,,8.719208238621495e-06,0.8364983797073364
+2025-06-04T15:58:09.988318,1,840,840,0.11472301930189133,1.1215627433141526,,,8.675367837977848e-06,0.8123106360435486
+2025-06-04T15:58:30.937925,1,850,850,0.0726587325334549,1.075363487714223,,,8.630903932522496e-06,0.6372828483581543
+2025-06-04T15:58:34.799348,1,860,860,0.19452973455190659,1.214739602085798,,,8.585824065298806e-06,1.091491937637329
+2025-06-04T15:58:38.677190,1,870,870,0.14252465218305588,1.1531815090486186,,,8.540135883844483e-06,0.9200571179389954
+2025-06-04T15:58:42.542710,1,880,880,0.12328824773430824,1.1312104428048655,,,8.49384713889421e-06,0.8436995148658752
+2025-06-04T15:58:46.420788,1,890,890,0.055943405255675316,1.057537830959794,,,8.44696568306478e-06,0.5423739552497864
+2025-06-04T15:59:07.372567,1,900,900,0.10158522799611092,1.106924255307932,,,8.399499469522947e-06,0.7847106456756592
+2025-06-04T15:59:11.254678,1,910,910,0.17052586376667023,1.1859283241106406,,,8.35145655063621e-06,0.9354358911514282
+2025-06-04T15:59:15.130113,1,920,920,0.10208459198474884,1.107477151455906,,,8.302845076606786e-06,0.7604900598526001
+2025-06-04T15:59:19.010625,1,930,930,0.11179571971297264,1.1182843938532543,,,8.253673294088968e-06,0.7490450143814087
+2025-06-04T15:59:22.889396,1,940,940,0.12244100123643875,1.1302524346106964,,,8.203949544790131e-06,0.8755216002464294
+2025-06-04T15:59:43.808026,1,950,950,0.12281830981373787,1.130678969011272,,,8.15368226405561e-06,0.8605537414550781
+2025-06-04T15:59:47.687514,1,960,960,0.11029093712568283,1.1166028844400853,,,8.10287997943769e-06,0.8044679760932922
+2025-06-04T15:59:51.545996,1,970,970,0.13130095973610878,1.1403109173471018,,,8.051551309248961e-06,0.9222280383110046
+2025-06-04T15:59:55.422269,1,980,980,0.06533852592110634,1.067520346530895,,,7.999704961100267e-06,0.6003274321556091
+2025-06-04T15:59:59.299502,1,990,990,0.1481747031211853,1.1597154845809048,,,7.947349730423509e-06,1.0037659406661987
+2025-06-04T16:00:20.173458,1,1000,1000,0.09115409478545189,1.095437793505203,,,7.894494498979558e-06,0.6946194767951965
+2025-06-04T16:00:24.034851,1,1010,1010,0.06985310651361942,1.0723506483588616,,,7.841148233351512e-06,0.6094436645507812
+2025-06-04T16:00:27.914051,1,1020,1020,0.21721255779266357,1.2426082001248913,,,7.787319983423564e-06,1.39258873462677
+2025-06-04T16:00:31.789968,1,1030,1030,0.08021197468042374,1.0835167214444683,,,7.733018880845747e-06,0.6262266635894775
+2025-06-04T16:00:35.650779,1,1040,1040,0.10484625026583672,1.1105398520219913,,,7.678254137484797e-06,0.8431848287582397
+2025-06-04T16:00:56.555193,1,1050,1050,0.16010309010744095,1.1736318545895827,,,7.623035043861422e-06,0.9451720118522644
+2025-06-04T16:01:00.436999,1,1060,1060,0.1360699161887169,1.1457619981066123,,,7.56737096757421e-06,0.8864161968231201
+2025-06-04T16:01:04.301305,1,1070,1070,0.08098086714744568,1.0843501496567565,,,7.511271351710476e-06,0.653930127620697
+2025-06-04T16:01:08.178934,1,1080,1080,0.10546499118208885,1.1112272010911335,,,7.4547457132442895e-06,0.7293416857719421
+2025-06-04T16:01:12.060376,1,1090,1090,0.23945699632167816,1.2705590447386081,,,7.39780364142199e-06,1.1615322828292847
+2025-06-04T16:01:33.008327,1,1100,1100,0.21317905187606812,1.2376062271230202,,,7.34045479613541e-06,1.1265214681625366
+2025-06-04T16:01:36.893071,1,1110,1110,0.22858554869890213,1.2568210399376758,,,7.2827089062831424e-06,1.2193849086761475
+2025-06-04T16:01:40.775666,1,1120,1120,0.17008887976408005,1.185410205617777,,,7.2245757681200835e-06,0.9430868029594421
+2025-06-04T16:01:44.639926,1,1130,1130,0.21848519518971443,1.2441905964850732,,,7.166065243595556e-06,1.2422202825546265
+2025-06-04T16:01:48.524440,1,1140,1140,0.12940853089094162,1.1381550006775147,,,7.107187258680288e-06,0.843524694442749
+2025-06-04T16:02:09.509814,1,1150,1150,0.12559930607676506,1.1338277593564878,,,7.047951801682533e-06,0.9139230251312256
+2025-06-04T16:02:13.394615,1,1160,1160,0.1010470874607563,1.1063287347478317,,,6.988368921553601e-06,0.7504018545150757
+2025-06-04T16:02:17.263516,1,1170,1170,0.08690540492534637,1.0907934911460626,,,6.928448726183121e-06,0.9263979196548462
+2025-06-04T16:02:21.133390,1,1180,1180,0.11731548048555851,1.1244741233805684,,,6.8682013806842985e-06,0.8856023550033569
+2025-06-04T16:02:25.015896,1,1190,1190,0.1063197422772646,1.1121774298049192,,,6.807637105669454e-06,0.807375431060791
+2025-06-04T16:02:46.062152,1,1200,1200,0.17924988269805908,1.196319646402064,,,6.746766175516159e-06,1.0243499279022217
+2025-06-04T16:02:49.946916,1,1210,1210,0.09139541536569595,1.0957021770884698,,,6.685598916624254e-06,0.7833459973335266
+2025-06-04T16:02:53.829310,1,1220,1220,0.1082618460059166,1.114339492533743,,,6.624145705664024e-06,0.7323276996612549
+2025-06-04T16:02:57.716753,1,1230,1230,0.05634104833006859,1.0579584371742161,,,6.562416967815863e-06,0.5661768317222595
+2025-06-04T16:03:01.603285,1,1240,1240,0.1578119546175003,1.1709459830181594,,,6.500423175001705e-06,1.0235848426818848
+2025-06-04T16:03:22.665669,1,1250,1250,0.11713567562401295,1.124271955642418,,,6.438174844108515e-06,0.9373230338096619
+2025-06-04T16:03:26.553201,1,1260,1260,0.09851735457777977,1.1035335555871335,,,6.375682535204168e-06,0.7698451280593872
+2025-06-04T16:03:30.438345,1,1270,1270,0.11661957576870918,1.1236918687530446,,,6.312956849745993e-06,0.9150201678276062
+2025-06-04T16:03:34.327490,1,1280,1280,0.12427449226379395,1.1323266432485943,,,6.2500084287822925e-06,0.8793236017227173
+2025-06-04T16:03:38.211254,1,1290,1290,0.17418143153190613,1.1902714990126755,,,6.1868479511471565e-06,1.0391594171524048
+2025-06-04T16:03:59.309946,1,1300,1300,0.11626759171485901,1.1232964167342876,,,6.123486131648859e-06,0.8350743055343628
+2025-06-04T16:04:03.199855,1,1310,1310,0.07747054845094681,1.080550408106575,,,6.059933719252151e-06,0.6586312651634216
+2025-06-04T16:04:07.092124,1,1320,1320,0.07231690175831318,1.0749959581996869,,,5.996201495254757e-06,0.6390174627304077
+2025-06-04T16:04:10.986353,1,1330,1330,0.08034726977348328,1.083663325857333,,,5.932300271458406e-06,0.6472488641738892
+2025-06-04T16:04:14.873661,1,1340,1340,0.09573419578373432,1.100466516475581,,,5.8682408883346535e-06,0.8322047591209412
+2025-06-04T16:04:32.200653,1,2681,1340,0.20949130744826217,1.23305065670761,0.2135066479294492,1.2380117284553571,5.8682408883346535e-06,
+2025-06-04T16:04:57.217038,2,10,1350,0.09219155833125114,1.0965748600131928,,,5.8040342131858654e-06,0.7483306527137756
+2025-06-04T16:05:01.111916,2,20,1360,0.05083961598575115,1.0521541310470375,,,5.73969113830165e-06,0.6238669753074646
+2025-06-04T16:05:04.997146,2,30,1370,0.07681288383901119,1.079840001971844,,,5.675222579111037e-06,0.704855740070343
+2025-06-04T16:05:08.893108,2,40,1380,0.07093845680356026,1.0735151562811673,,,5.610639472330737e-06,0.7362458109855652
+2025-06-04T16:05:12.780723,2,50,1390,0.07507956400513649,1.0779699150765751,,,5.545952774109798e-06,0.7241469025611877
+2025-06-04T16:05:33.899301,2,60,1400,0.10019706189632416,1.1053887266127027,,,5.481173458170952e-06,0.9513847827911377
+2025-06-04T16:05:37.785001,2,70,1410,0.04052358120679855,1.0413558658410078,,,5.4163125139489896e-06,0.5646671056747437
+2025-06-04T16:05:41.673972,2,80,1420,0.13121213763952255,1.140209637038694,,,5.351380944726465e-06,0.9856654405593872
+2025-06-04T16:05:45.562491,2,90,1430,0.11307748407125473,1.119718689950157,,,5.286389765767056e-06,0.9123920202255249
+2025-06-04T16:05:49.453509,2,100,1440,0.0894496887922287,1.0935723129844412,,,5.221350002446882e-06,0.822655975818634
+2025-06-04T16:06:10.573961,2,110,1450,0.04346796963363886,1.044426540411532,,,5.156272688384123e-06,0.5520569682121277
+2025-06-04T16:06:14.466564,2,120,1460,0.13778063654899597,1.1477237540142602,,,5.0911688635672155e-06,1.0230581760406494
+2025-06-04T16:06:18.326786,2,130,1470,0.07549739256501198,1.0784204158032615,,,5.026049572482002e-06,0.7364359498023987
+2025-06-04T16:06:22.218793,2,140,1480,0.13180837780237198,1.1408896785322435,,,4.96092586223808e-06,1.1415563821792603
+2025-06-04T16:06:26.103407,2,150,1490,0.05570453219115734,1.0572852438266014,,,4.895808780694738e-06,0.7476668953895569
+2025-06-04T16:06:47.262701,2,160,1500,0.08492013439536095,1.0886301191236925,,,4.8307093745867335e-06,0.8331665992736816
+2025-06-04T16:06:51.160457,2,170,1510,0.09430919960141182,1.0988994726717203,,,4.765638687650299e-06,0.8835126161575317
+2025-06-04T16:06:55.051079,2,180,1520,0.039034622721374035,1.0398064839571168,,,4.700607758749626e-06,0.5312080383300781
+2025-06-04T16:06:58.947587,2,190,1530,0.09536056965589523,1.1000554302332763,,,4.635627620004178e-06,0.8708493709564209
+2025-06-04T16:07:02.832561,2,200,1540,0.058465560898184776,1.0602084724383314,,,4.57070929491717e-06,0.6560453176498413
+2025-06-04T16:07:23.955276,2,210,1550,0.07735063508152962,1.0804208434347373,,,4.5058637965054905e-06,0.8640308976173401
+2025-06-04T16:07:27.848027,2,220,1560,0.07625348679721355,1.0792361115921199,,,4.441102125431398e-06,0.829659640789032
+2025-06-04T16:07:31.737333,2,230,1570,0.10900850594043732,1.1151718358863194,,,4.3764352681363365e-06,0.9264845252037048
+2025-06-04T16:07:35.631800,2,240,1580,0.05006047524511814,1.051334674175685,,,4.311874194977142e-06,0.6202943921089172
+2025-06-04T16:07:39.521053,2,250,1590,0.08443677611649036,1.0881040478936708,,,4.247429858364981e-06,0.865699291229248
+2025-06-04T16:08:00.602207,2,260,1600,0.08922336995601654,1.093324844975645,,,4.183113190907349e-06,0.9664984941482544
+2025-06-04T16:08:04.490320,2,270,1610,0.10598694533109665,1.111807362134794,,,4.11893510355341e-06,1.0453600883483887
+2025-06-04T16:08:08.355443,2,280,1620,0.08416618593037128,1.0878096574482132,,,4.054906483743012e-06,0.7608398199081421
+2025-06-04T16:08:12.233929,2,290,1630,0.08983586728572845,1.0939947086476136,,,3.99103819355971e-06,0.8169810175895691
+2025-06-04T16:08:16.116204,2,300,1640,0.10179191827774048,1.1071530694400182,,,3.927341067888065e-06,0.9132513999938965
+2025-06-04T16:08:37.120057,2,310,1650,0.08725733309984207,1.0911774396653415,,,3.863825912575573e-06,0.8127678632736206
+2025-06-04T16:08:41.005250,2,320,1660,0.08614224568009377,1.0899613595734716,,,3.800503502599511e-06,0.9069166779518127
+2025-06-04T16:08:44.869929,2,330,1670,0.09273252263665199,1.097168228351735,,,3.7373845802390394e-06,1.0052939653396606
+2025-06-04T16:08:48.751768,2,340,1680,0.08590411208570004,1.0897018340592644,,,3.6744798532528137e-06,0.8956423997879028
+2025-06-04T16:08:52.632466,2,350,1690,0.04824352078139782,1.0494261812939538,,,3.611799993062497e-06,0.5963554382324219
+2025-06-04T16:09:13.541304,2,360,1700,0.053508270531892776,1.0549657168591178,,,3.549355632942405e-06,0.6234306693077087
+2025-06-04T16:09:17.416341,2,370,1710,0.04932752437889576,1.0505643798439919,,,3.4871573662156287e-06,0.5964241623878479
+2025-06-04T16:09:21.296846,2,380,1720,0.07632846012711525,1.079317028550425,,,3.4252157444569478e-06,0.8359777331352234
+2025-06-04T16:09:25.173247,2,390,1730,0.04537820816040039,1.0464235510034243,,,3.363541275702818e-06,0.6145345568656921
+2025-06-04T16:09:29.055844,2,400,1740,0.09098780155181885,1.0952556447577493,,,3.3021444226687267e-06,0.8584290742874146
+2025-06-04T16:09:49.952086,2,410,1750,0.049650244414806366,1.050903472731473,,,3.2410356009742784e-06,0.6375706791877747
+2025-06-04T16:09:53.834130,2,420,1760,0.08727036416530609,1.0911916589626367,,,3.1802251773762294e-06,0.8463383316993713
+2025-06-04T16:09:57.714735,2,430,1770,0.07331629283726215,1.076070836592692,,,3.119723468009829e-06,0.7825964093208313
+2025-06-04T16:10:01.573670,2,440,1780,0.08756432309746742,1.0915124716480558,,,3.059540736638751e-06,0.851995587348938
+2025-06-04T16:10:05.448649,2,450,1790,0.039396269246935844,1.0401825943647085,,,2.9996871929139104e-06,0.5352329015731812
+2025-06-04T16:10:26.369149,2,460,1800,0.04152260348200798,1.0423967233807683,,,2.9401729906414385e-06,0.5729257464408875
+2025-06-04T16:10:30.245596,2,470,1810,0.07019095867872238,1.0727130055552943,,,2.881008226060168e-06,0.7474201917648315
+2025-06-04T16:10:34.126508,2,480,1820,0.04946332424879074,1.050707056037576,,,2.822202936128858e-06,0.6267549991607666
+2025-06-04T16:10:38.001835,2,490,1830,0.11550524644553661,1.122440403355276,,,2.76376709682347e-06,0.9410679340362549
+2025-06-04T16:10:41.879393,2,500,1840,0.06606614962220192,1.06829738229697,,,2.7057106214448216e-06,0.7640741467475891
+2025-06-04T16:11:02.820833,2,510,1850,0.06857362389564514,1.0709794717293049,,,2.6480433589368424e-06,0.7982816696166992
+2025-06-04T16:11:06.705971,2,520,1860,0.11946064792573452,1.126888897779058,,,2.5907750922157555e-06,1.1855436563491821
+2025-06-04T16:11:10.581562,2,530,1870,0.05941667780280113,1.0612173343356341,,,2.533915536510464e-06,0.7668613195419312
+2025-06-04T16:11:14.457155,2,540,1880,0.07246024534106255,1.0751500630164808,,,2.4774743377144265e-06,0.7726814150810242
+2025-06-04T16:11:18.318211,2,550,1890,0.07262087985873222,1.075322783100308,,,2.4214610707492752e-06,0.8308311700820923
+2025-06-04T16:11:39.197748,2,560,1900,0.08977160044014454,1.0939244033177784,,,2.3658852379404973e-06,0.8458873629570007
+2025-06-04T16:11:43.081320,2,570,1910,0.04722259379923344,1.0483553405078179,,,2.3107562674054122e-06,0.6285303831100464
+2025-06-04T16:11:46.958811,2,580,1920,0.05732823722064495,1.0590033576721796,,,2.256083511453747e-06,0.7101243734359741
+2025-06-04T16:11:50.838620,2,590,1930,0.056910332292318344,1.0585608874115848,,,2.20187624500108e-06,0.6693544983863831
+2025-06-04T16:11:54.715259,2,600,1940,0.075874924659729,1.078827630985389,,,2.1481436639953983e-06,0.7663268446922302
+2025-06-04T16:12:15.657974,2,610,1950,0.08494022488594055,1.0886519904565477,,,2.094894883857051e-06,0.8211141228675842
+2025-06-04T16:12:19.543490,2,620,1960,0.069455586373806,1.0719244520956086,,,2.042138937932388e-06,0.7399444580078125
+2025-06-04T16:12:23.418781,2,630,1970,0.043883929029107094,1.0448610698109204,,,1.989884775961296e-06,0.5605442523956299
+2025-06-04T16:12:27.278023,2,640,1980,0.05252310447394848,1.0539269122241246,,,1.9381412625589237e-06,0.641305148601532
+2025-06-04T16:12:31.134662,2,650,1990,0.06824682280421257,1.0706295316525558,,,1.8869171757118554e-06,0.8991125226020813
+2025-06-04T16:12:52.061672,2,660,2000,0.056670188903808594,1.0583067115336877,,,1.8362212052889827e-06,0.6741258502006531
+2025-06-04T16:12:55.944385,2,670,2010,0.05249423906207085,1.0538964906287824,,,1.7860619515673034e-06,0.6633082032203674
+2025-06-04T16:12:59.824036,2,680,2020,0.07438912987709045,1.0772259047328216,,,1.7364479237729526e-06,0.8070685863494873
+2025-06-04T16:13:03.700676,2,690,2030,0.05695551820099354,1.0586087205278538,,,1.6873875386376464e-06,0.6835163235664368
+2025-06-04T16:13:07.561493,2,700,2040,0.08398167788982391,1.0876089663349604,,,1.63888911897084e-06,0.8436160683631897
+2025-06-04T16:13:28.476986,2,710,2050,0.03553978633135557,1.0361788730639523,,,1.5909608922478108e-06,0.5797974467277527
+2025-06-04T16:13:32.359636,2,720,2060,0.07211183197796345,1.07477553161685,,,1.5436109892139178e-06,0.7558038830757141
+2025-06-04T16:13:36.239867,2,730,2070,0.0650089755654335,1.0671686027828295,,,1.4968474425052576e-06,0.7757009863853455
+2025-06-04T16:13:40.124392,2,740,2080,0.09436911717057228,1.0989653180295018,,,1.4506781852859836e-06,0.884422779083252
+2025-06-04T16:13:44.008383,2,750,2090,0.0381308626383543,1.038867172882713,,,1.4051110499024923e-06,0.536321222782135
+2025-06-04T16:14:05.013950,2,760,2100,0.045937731862068176,1.0470092136129705,,,1.360153766554701e-06,0.6449976563453674
+2025-06-04T16:14:08.897170,2,770,2110,0.08238577656447887,1.0858746340238439,,,1.3158139619846734e-06,1.050763726234436
+2025-06-04T16:14:12.773031,2,780,2120,0.06662464700639248,1.068894190232843,,,1.2720991581827852e-06,0.7440298199653625
+2025-06-04T16:14:16.639486,2,790,2130,0.0670732781291008,1.0693738370176564,,,1.229016771111658e-06,0.7524603009223938
+2025-06-04T16:14:20.526197,2,800,2140,0.17072025686502457,1.1861588828007739,,,1.186574109448091e-06,1.283272385597229
+2025-06-04T16:14:41.599092,2,810,2150,0.07225818186998367,1.074932836410337,,,1.1447783733431799e-06,0.8511999845504761
+2025-06-04T16:14:45.469048,2,820,2160,0.05403805337846279,1.0555247676743196,,,1.1036366532008552e-06,0.6990443468093872
+2025-06-04T16:14:49.353694,2,830,2170,0.07556630671024323,1.0784947367852706,,,1.0631559284750398e-06,0.7718824744224548
+2025-06-04T16:14:53.235127,2,840,2180,0.07645644620060921,1.0794551749391827,,,1.0233430664856236e-06,0.8092624545097351
+2025-06-04T16:14:57.121511,2,850,2190,0.0467569287866354,1.0478672717520643,,,9.842048212534567e-07,0.6216375827789307
+2025-06-04T16:15:18.200082,2,860,2200,0.08881667256355286,1.0928802830192994,,,9.457478323545749e-07,0.910168468952179
+2025-06-04T16:15:22.090252,2,870,2210,0.09652426838874817,1.1013363084771548,,,9.07978623793836e-07,0.9564467072486877
+2025-06-04T16:15:25.974800,2,880,2220,0.03395761735737324,1.0345407592276568,,,8.709036028981571e-07,0.5178916454315186
+2025-06-04T16:15:29.860619,2,890,2230,0.053766580298542976,1.0552382600060264,,,8.345290592295429e-07,0.6506232619285583
+2025-06-04T16:15:33.750074,2,900,2240,0.06971279717981815,1.0722001981088232,,,7.988611635181099e-07,0.7732512950897217
+2025-06-04T16:15:54.818147,2,910,2250,0.10275266878306866,1.1082172784487707,,,7.639059666152526e-07,0.9805467128753662
+2025-06-04T16:15:58.707863,2,920,2260,0.09875445626676083,1.1037952362782515,,,7.296693984671465e-07,1.038161277770996
+2025-06-04T16:16:02.576727,2,930,2270,0.0979168489575386,1.1028710764160194,,,6.961572671087741e-07,0.9988915920257568
+2025-06-04T16:16:06.465591,2,940,2280,0.09837886318564415,1.1033807362710761,,,6.633752576786251e-07,0.9663264155387878
+2025-06-04T16:16:10.358347,2,950,2290,0.03254261892288923,1.033077920874007,,,6.313289314542392e-07,0.5405398607254028
+2025-06-04T16:16:31.505418,2,960,2300,0.03980386257171631,1.0406066522624378,,,6.000237249087776e-07,0.5731000304222107
+2025-06-04T16:16:35.400262,2,970,2310,0.08755393698811531,1.0915011351390373,,,5.694649487887466e-07,0.9045767188072205
+2025-06-04T16:16:39.293181,2,980,2320,0.0784428808838129,1.0816015732718982,,,5.396577872130676e-07,0.832079291343689
+2025-06-04T16:16:43.181234,2,990,2330,0.06308055575937033,1.0651126367327846,,,5.106072967936188e-07,0.8090586066246033
+2025-06-04T16:16:47.070248,2,1000,2340,0.08401019498705864,1.0876399822278462,,,4.823184057774116e-07,0.8339213132858276
+2025-06-04T16:17:08.123786,2,1010,2350,0.10523340478539467,1.1109698857842367,,,4.5479591321053895e-07,0.9590398669242859
+2025-06-04T16:17:11.996628,2,1020,2360,0.15093089640140533,1.1629162936043624,,,4.2804448812404754e-07,1.2930185794830322
+2025-06-04T16:17:15.862961,2,1030,2370,0.044746036641299725,1.0457622408902971,,,4.020686687418651e-07,0.7421437501907349
+2025-06-04T16:17:19.746935,2,1040,2380,0.07852279394865036,1.0816880108222502,,,3.7687286171091355e-07,0.8390912413597107
+2025-06-04T16:17:23.600032,2,1050,2390,0.08741313591599464,1.0913474614279544,,,3.5246134135354934e-07,0.8625169396400452
+2025-06-04T16:17:44.673962,2,1060,2400,0.09790205955505371,1.1028547657323942,,,3.288382489424502e-07,0.9403291344642639
+2025-06-04T16:17:48.563786,2,1070,2410,0.08274862542748451,1.0862687138915583,,,3.0600759199806815e-07,0.8528719544410706
+2025-06-04T16:17:52.433486,2,1080,2420,0.12123417109251022,1.1288892346432176,,,2.839732436087833e-07,1.396231770515442
+2025-06-04T16:17:56.301147,2,1090,2430,0.05448045115917921,1.0559918327956987,,,2.6273894177385074e-07,0.6799153089523315
+2025-06-04T16:18:00.185705,2,1100,2440,0.041266513988375664,1.0421298107099377,,,2.4230828876927293e-07,0.5852925181388855
+2025-06-04T16:18:21.293365,2,1110,2450,0.08677143976092339,1.0906473726042856,,,2.2268475053669803e-07,0.9448606371879578
+2025-06-04T16:18:25.186404,2,1120,2460,0.04151636362075806,1.0423902189901402,,,2.0387165609543736e-07,0.6255165934562683
+2025-06-04T16:18:29.077248,2,1130,2470,0.07429993152618408,1.0771298222438292,,,1.8587219697771942e-07,0.9192423820495605
+2025-06-04T16:18:32.966138,2,1140,2480,0.07785939425230026,1.0809706572966895,,,1.6868942668726408e-07,0.8874773979187012
+2025-06-04T16:18:36.856620,2,1150,2490,0.05496346019208431,1.0565020095896944,,,1.5232626018127582e-07,0.6460995078086853
+2025-06-04T16:18:57.884077,2,1160,2500,0.09730996191501617,1.1022019613093508,,,1.3678547337593494e-07,0.8977996706962585
+2025-06-04T16:19:01.766719,2,1170,2510,0.050714531913399696,1.0520225315542564,,,1.2206970267548078e-07,0.6345444321632385
+2025-06-04T16:19:05.649466,2,1180,2520,0.11084700748324394,1.1172239668720507,,,1.0818144452496293e-07,0.9890771508216858
+2025-06-04T16:19:09.538711,2,1190,2530,0.06192183867096901,1.063879187267022,,,9.512305498672936e-08,0.6979386806488037
+2025-06-04T16:19:13.424704,2,1200,2540,0.11293324083089828,1.1195571897459673,,,8.289674934073844e-08,1.0071110725402832
+2025-06-04T16:19:34.488446,2,1210,2550,0.07455204799771309,1.077401418649517,,,7.150460170874895e-08,0.790630578994751
+2025-06-04T16:19:38.381800,2,1220,2560,0.03821308817714453,1.0389525978077419,,,6.094854470245326e-08,0.6562174558639526
+2025-06-04T16:19:42.266736,2,1230,2570,0.08794312551617622,1.0919260175335126,,,5.123036909562673e-08,0.8555896878242493
+2025-06-04T16:19:46.155691,2,1240,2580,0.05262951739132404,1.0540390696289477,,,4.235172352033024e-08,0.691398561000824
+2025-06-04T16:19:50.041245,2,1250,2590,0.08566490188241005,1.089441197436726,,,3.431411418722941e-08,0.8565791845321655
+2025-06-04T16:20:11.046606,2,1260,2600,0.05852423422038555,1.0602706802165853,,,2.711890463007405e-08,0.6980656981468201
+2025-06-04T16:20:14.937058,2,1270,2610,0.052355626598000526,1.053750417563349,,,2.076731547438593e-08,0.6781346201896667
+2025-06-04T16:20:18.817416,2,1280,2620,0.0786192286759615,1.0817923281404347,,,1.5260424230382763e-08,0.8754461407661438
+2025-06-04T16:20:22.700789,2,1290,2630,0.09569213911890984,1.1004202354973656,,,1.0599165110186105e-08,0.8618500828742981
+2025-06-04T16:20:26.583343,2,1300,2640,0.07639635913074017,1.0793903155892892,,,6.784328869339218e-09,0.8118147253990173
+2025-06-04T16:20:47.500884,2,1310,2650,0.05080252140760422,1.052115102557278,,,3.816562672658841e-09,0.6867138743400574
+2025-06-04T16:20:51.383803,2,1320,2660,0.06145966425538063,1.0633876031329454,,,1.6963699844474434e-09,0.7489965558052063
+2025-06-04T16:20:55.262606,2,1330,2670,0.051951976493000984,1.0533251569306799,,,4.2411048308210744e-10,0.6713370680809021
+2025-06-04T16:20:59.142862,2,1340,2680,0.08062903303653002,1.0839687053924174,,,0.0,0.81634920835495

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece005a0b347ec0097dd97e49f6420d0e1a7da7fb8e2352072e226453e90dd07
+size 4996670464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e9e88070bddad6e6245d3c532fe3058406fc5c498fa36bacdce2e67e4db6ff
+size 1178224960

model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+  "metadata": {
+    "total_size": 6174857216
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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
+}