Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,50 @@
+---
+language:
+- en
+- zh
+- ko
+license: apache-2.0
+base_model: Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2
+tags:
+- unsloth
+- qwen
+- qwen3.5
+- reasoning
+- chain-of-thought
+- lora
+- mlx
+pipeline_tag: text-generation
+datasets:
+- nohurry/Opus-4.6-Reasoning-3000x-filtered
+- Jackrong/Qwen3.5-reasoning-700x
+- Roman1111111/claude-opus-4.6-10000x
+library_name: mlx
+---
+
+# Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-bf16
+
+This model [Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-bf16](https://huggingface.co/Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-bf16) was
+converted to MLX format from [Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2](https://huggingface.co/Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2)
+using mlx-lm version **0.30.7**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-bf16")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_dict=False,
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,88 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant
+<think>
+' }}
+{%- endif %}

config.json

@@ -0,0 +1,97 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "eos_token_id": 248046,
+    "image_token_id": 248056,
+    "model_name": "unsloth/Qwen3.5-4B",
+    "model_type": "qwen3_5",
+    "pad_token_id": 248055,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": null,
+        "torch_dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 2560,
+        "initializer_range": 0.02,
+        "intermediate_size": 9216,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_hidden_layers": 32,
+        "num_key_value_heads": 4,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "type": "default"
+        },
+        "tie_word_embeddings": true,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.3.4",
+    "use_cache": false,
+    "video_token_id": 248057,
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af77ca68b0d7cd7872375ad4c2c8be301e75d43da9af8bcec54f36df4580aba
+size 5356483890

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e22fc1303975ee65b6bef9b51a36598a092ed4bfc5ca651547ce7bb399c360
+size 3055074269

model.safetensors.index.json

@@ -0,0 +1,434 @@
+{
+    "metadata": {
+        "total_size": 8411502592,
+        "total_parameters": 4205749760
+    },
+    "weight_map": {
+        "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "json_tools",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}