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 +1,38 @@
+---
+tags:
+- unsloth
+- mlx
+base_model: unsloth/Qwen3.5-397B-A17B
+library_name: mlx
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/LICENSE
+pipeline_tag: text-generation
+---
+
+# async0x42/Qwen3.5-397B-A17B
+
+This model [async0x42/Qwen3.5-397B-A17B](https://huggingface.co/async0x42/Qwen3.5-397B-A17B) was
+converted to MLX format from [unsloth/Qwen3.5-397B-A17B](https://huggingface.co/unsloth/Qwen3.5-397B-A17B)
+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("async0x42/Qwen3.5-397B-A17B")
+
+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 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,1100 @@
+{
+    "architectures": [
+        "Qwen3_5MoeForConditionalGeneration"
+    ],
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "image_token_id": 248056,
+    "model_type": "qwen3_5_moe",
+    "pad_token_id": 248055,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.40.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.40.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.41.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.41.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.42.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.42.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.43.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.43.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.44.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.44.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.45.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.45.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.46.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.46.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.47.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.47.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.48.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.48.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.49.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.49.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.50.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.50.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.51.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.51.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.52.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.52.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.53.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.53.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.54.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.54.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.55.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.55.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.56.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.56.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.57.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.57.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.58.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.58.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.59.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.59.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.40.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.40.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.41.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.41.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.42.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.42.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.43.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.43.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.44.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.44.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.45.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.45.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.46.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.46.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.47.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.47.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.48.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.48.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.49.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.49.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.50.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.50.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.51.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.51.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.52.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.52.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.53.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.53.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.54.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.54.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.55.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.55.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.56.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.56.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.57.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.57.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.58.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.58.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.59.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.59.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "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": 4096,
+        "initializer_range": 0.02,
+        "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_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": 64,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_moe_text",
+        "moe_intermediate_size": 1024,
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 32,
+        "num_experts": 512,
+        "num_experts_per_tok": 10,
+        "num_hidden_layers": 60,
+        "num_key_value_heads": 2,
+        "output_router_logits": false,
+        "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"
+        },
+        "router_aux_loss_coef": 0.001,
+        "shared_expert_intermediate_size": 1024,
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "5.2.0.dev0",
+    "unsloth_fixed": true,
+    "video_token_id": 248057,
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 0.6,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "4.57.0.dev0"
+}

model-00001-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456f43273664ed997cfac6afd3f2bf87128a58e446638d22ebd4558dc0e0b065
+size 4340497708

model-00003-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596c6caf10767f1908374ee29d296050621e64071677381c692cf43cec988950
+size 4900154294

model-00004-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e2052a9b7d86701e0545489d59d64989bfde88fc6418bd01beb99f518dc69f
+size 4983411966

model-00005-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc5539bf604b1ed55831b20372f25ae7cd5f11c3c0fe9337579cb78d63e9d15
+size 4907625938

model-00006-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3261a10f09f2d7f6940e487fa386d0a6e28a099a303725ea3ad99b9756b995e
+size 4900154304

model-00008-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1466d947b41bf0adec40b83ba757d872231c5de695a113f99bf70024bb9288e
+size 4907625991

model-00009-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07cf03eeb0e5330be24517bfd174b74fa390496fa7ad34f2a333ff0448078a94
+size 4900154335

model-00010-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9370421c66939b687cb5b80ba13bde37ea7058a5a6ab8c5238ac8d86dff21de
+size 4983412044

model-00011-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6b965542c00d00a830e5c7ac0dc8ba67f214ae9c12909d2563af5f5bc5a6cd
+size 4907626042

model-00012-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b41683da8a88716fc09a276ffbc6d5f586b51aab4b50b699d7d92a0382ee68d
+size 4900154341

model-00013-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f945159c34c3950861377047d0a76fddf03d52b86f8538a952dd41f501bf1584
+size 4983412006

model-00014-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cb948d81783b7af0adaf26ac0ce3b2a3b2f0947668c7758381c5a7d88f27ca
+size 4907625982

model-00015-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0835c4b9255019cf18953e5ddb53cf9ea4b859fb075e123dced68d92006d8ae7
+size 4900154347

model-00016-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a37f302b1a143e2188fa41b1dcca5195831013dde094ac90f21276276e1d23
+size 4983412022

model-00017-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe9a433436778b03390b191992b3288aab11dfdda0215bd855cacbcbb4fabca
+size 4907625978

model-00018-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6cf934936edc29c7e8ecb9ab269e19d0b372134e20608c17bc6fd0ab90e9fe
+size 4900154337

model-00019-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f67f0e735e6bc7c7302f6de5291c626be427b33cac75b38d21e02b4d66bd87
+size 4983412026

model-00020-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75dfea398d0a2ce6f7f7cc1414ab87ad055ae36367afe3854393005e9e48d446
+size 4907626030

model-00021-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b4207945236e718ecf672a027caea75a681ae18675fd0a7380fb7552a28cdb
+size 4900154317

model-00022-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2426aeb3633c89d528802a2f1f50e502e393595aad160bf3c8a7e50e91988cf6
+size 4983412020

model-00023-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb02b479cc6536a7a9050473900bc9ea57a4d7fe0bb68a0ffe2226ac58d053ad
+size 4907626038

model-00024-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da885e4fc646e7f6f07e4d17f8adf430041bc352eb446a0b3eb15e994c4f75b6
+size 4900154347

model-00025-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e1a1a8ab8acffaa5f02cbe1cecee65786e77a08c12f33025f59dbc33029e33
+size 4983412042

model-00026-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecca87d3e1c65e84850288367ec225b3f153a5571f05679a8802f1e02fa2beda
+size 4907626030

model-00027-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d5f543cae9d2632bc3047c9b0de42ae64f6e481ddf31019ab21f34cd009da6
+size 4900154347

model-00028-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e832ef6e4e001da92ba51db5fc08f6c96297a713c6da712248de8ffb100e0a08
+size 4983412016

model-00029-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c1ac245616cb92a74555e059e10d14c5cf9dc007756e00ace8cc0146c65988
+size 4907626034

model-00030-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd257dff03daa1c8405ab9c1d3c3496c4818a9b0926bcd8bf404d4b4f6d8c18b
+size 4900154331

model-00031-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90224fb9892156d31d97dd2b5645e6f770d0d66833e3e9c0ebb7cd72fc63babf
+size 4983412016

model-00032-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b11f7b31b86956085697c0d5ac21d4c5a6ec33357e8dd8ea7c31afafb01b2d
+size 4907625970

model-00033-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a5add9b57b9c94412c67571cda2156ffe15a505fc5943e582eb9b1d493452b
+size 4900154343

model-00034-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e122e0b84463927313096721a50e2725989878bbb6c46533966541f7f4f3e27
+size 4983411996

model-00035-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b75f8378deaa6215ad0aef360d8c78309324da4a36a9ec138e5cf805ac6bdc
+size 4907626016

model-00036-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54a7d707f3f4a7d05c855afab589ac8064b1528ce5afc4eb7a1e2e54079a44c
+size 4900154277

model-00037-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b79a88926ef85567e9929319aefd053aef0bf2555121b5fde8d98b5c254130c
+size 4983412018

model-00038-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1b469ede82e329ed09c8aee85d8a144281cbe2ca4f968a32d3dc22dc0ff153
+size 4907625958

model-00039-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9eb67fc3e83bd0b2381872d2d98c2dad7c4d06647dbf09ef177f1f2f330a7af
+size 4900154343

model-00040-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62675676f34af5108094e48de0edcaae330ec6c19076e371f335f0c11b0c92dd
+size 4983412050

model-00041-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e60f3b831c327015b7f8e137b31410ef2d9c7ffd700713bb820be6a6c7ab9f8
+size 4907625976

model-00042-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e94fabe68719c6b9a0c14ef94d1dd557409adafc366abd9a6f4c62234e7505
+size 4900154343

model-00044-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a42bfc9c34c4cc07756d9a2b2364629dc4cf5a2dbfd39c66cdb76063f393a2
+size 4907626038

model-00045-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd995517c9460cf792adc9a96a4b5ecc95e23f72c0d60602b10110d4ef3b7a1d
+size 4900154347

model-00046-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726cda5891e13d726197cd592f7586d11560db314e1adae6fcd270dddfaaab31
+size 1787181790

tokenizer.json

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