Upload Qwen3.5-9B MixedInt4 AutoRound

.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 +1,104 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.5-9B
+base_model_relation: quantized
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- qwen
+- qwen3.5
+- multimodal
+- autoround
+- quantization
+- int4
+---
+
+# Qwen3.5-9B Mixed-INT4 AutoRound
+
+This repository contains a Mixed-INT4 quantized version of
+[Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B), produced using
+[Intel AutoRound](https://github.com/intel/auto-round).
+
+The model weights were quantized to reduce memory requirements while preserving
+the original Qwen3.5 architecture, tokenizer, configuration, and multimodal
+capabilities.
+
+## Model Information
+
+* **Base model:** [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B)
+* **Model type:** Multimodal causal language model with vision encoder
+* **Quantization:** Mixed INT4
+* **Quantization framework:** Intel AutoRound
+* **Weight format:** Safetensors
+* **Native context length:** 262,144 tokens
+* **License:** Apache 2.0
+
+## Important Notice
+
+This repository is an unofficial community quantization of Qwen3.5-9B.
+
+The model architecture and original model behavior are provided by the Qwen
+team. Quantization may cause small differences in output quality, numerical
+precision, generation consistency, and benchmark performance compared with the
+original model.
+
+No independent benchmark results are currently provided for this quantized
+version.
+
+## Serving with vLLM
+
+If the installed vLLM version supports this model architecture and AutoRound
+quantization format, the model can be served using:
+
+```bash
+vllm serve YOUR_USERNAME/Qwen3.5-9B-MixedInt4-AutoRound \
+  --trust-remote-code
+```
+
+Support for newly released model architectures and quantization formats may
+require a recent development build of vLLM.
+
+## Quantization Details
+
+* **Method:** Mixed-INT4 AutoRound quantization
+* **Source weights:** Qwen/Qwen3.5-9B
+* **Fine-tuning:** None
+* **Architecture modifications:** None intended
+
+Exact quantization settings, calibration dataset, group size, and AutoRound
+version should be documented here when available.
+
+## Limitations
+
+This model inherits the limitations of the original Qwen3.5-9B model.
+
+Additional limitations may result from quantization:
+
+* Reduced numerical precision
+* Small changes in generated responses
+* Possible degradation on sensitive reasoning or vision-language tasks
+* Runtime compatibility differences between inference frameworks
+* Potential differences in long-context behavior
+
+Users should evaluate the model on their own workloads before production use.
+
+## Original Model
+
+For complete information about the architecture, supported languages, context
+length, multimodal usage, benchmarks, intended uses, and limitations, refer to
+the original model card:
+
+* [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B)
+
+## License
+
+The original Qwen3.5-9B model is distributed under the Apache License 2.0.
+
+This quantized repository follows the license and usage requirements of the
+original model. Users are responsible for reviewing and complying with the
+original license terms.
+
+## Credits
+
+* Original model: [Qwen](https://huggingface.co/Qwen)
+* Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round)

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 +1,300 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "quantization_config": {
+    "autoround_version": "0.14.2",
+    "bits": 4,
+    "block_name_to_quantize": [
+      "model.language_model.layers",
+      "mtp.layers"
+    ],
+    "data_type": "int",
+    "extra_config": {
+      "model.language_model.layers.0.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.0.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.0.linear_attn.in_proj_qkv": {
+        "bits": 8
+      },
+      "model.language_model.layers.0.linear_attn.in_proj_z": {
+        "bits": 8
+      },
+      "model.language_model.layers.0.linear_attn.out_proj": {
+        "bits": 8
+      },
+      "model.language_model.layers.1.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.1.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.1.linear_attn.out_proj": {
+        "bits": 8
+      },
+      "model.language_model.layers.10.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.10.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.11.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.language_model.layers.12.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.12.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.13.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.13.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.14.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.14.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.16.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.16.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.17.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.17.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.18.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.18.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.2.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.2.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.2.linear_attn.out_proj": {
+        "bits": 8
+      },
+      "model.language_model.layers.2.mlp.down_proj": {
+        "bits": 8
+      },
+      "model.language_model.layers.20.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.20.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.21.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.21.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.22.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.22.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.24.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.24.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.25.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.25.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.26.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.26.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.28.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.28.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.29.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.29.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.3.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.language_model.layers.30.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.30.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.4.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.4.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.5.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.5.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.6.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.6.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.7.self_attn.o_proj": {
+        "bits": 8
+      },
+      "model.language_model.layers.8.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.8.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "model.language_model.layers.9.linear_attn.in_proj_a": {
+        "bits": 8
+      },
+      "model.language_model.layers.9.linear_attn.in_proj_b": {
+        "bits": 8
+      },
+      "mtp.fc": {
+        "bits": 16,
+        "data_type": "fp"
+      }
+    },
+    "group_size": 32,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "scale_dtype": "None",
+    "sym": true
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "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,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.14.1",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": 248044,
+  "transformers_version": "5.14.1",
+  "use_cache": true
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29308dfb41d66389c406c941fe15b7e5e3a0fc1b1fb60443844588fd6a95ea5
+size 1067352584

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f440e6b5d27590497d0c1726121cda6bb12f32febec6b88d91dd75ee278acd83
+size 1068240424

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0aa5de9f30b9bf4fb3d31491240957391423c8e818e27c06830c6cb7be19d8c
+size 1069493496

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd27a2aab13ace929ce1f852bdd269d25d55594f9db290961e2e89e2d0572dfc
+size 1073191448

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf9f25bc2e249949974e0741a72771b4cd065bfe2221c98aff443c6547d7c8f
+size 742826888

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01f5aff6f0c0956b006370df5a0002afb8b0ee8f9996f4e18bbeac98893e8b3
+size 2034237568

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c003d5ad014b20ae5ec24a67352bd051d3d69a81ae549dd63a4c9ac5ed2e2f
+size 8296

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106ec926c62c1aac2c8ab808833db89012a9132c53f767fa7609ec69e377d4ab
+size 2034237536

model_extra_tensors.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ce1a16634a17dfe43dca1592c30d3f01b92e5dad06b5cc8d7313614382d75a
+size 188395560

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "merge_size": 2,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

quantization_config.json

@@ -0,0 +1,184 @@
+{
+  "bits": 4,
+  "data_type": "int",
+  "group_size": 32,
+  "sym": true,
+  "scale_dtype": "None",
+  "autoround_version": "0.14.2",
+  "block_name_to_quantize": "model.language_model.layers",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq",
+  "extra_config": {
+    "model.language_model.layers.0.linear_attn.in_proj_qkv": {
+      "bits": 8
+    },
+    "model.language_model.layers.0.linear_attn.in_proj_z": {
+      "bits": 8
+    },
+    "model.language_model.layers.0.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.0.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.1.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.1.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.2.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.2.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.4.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.4.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.5.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.5.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.6.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.6.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.8.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.8.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.9.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.9.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.10.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.10.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.12.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.12.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.13.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.13.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.14.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.14.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.16.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.16.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.17.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.17.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.18.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.18.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.20.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.20.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.21.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.21.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.22.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.22.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.24.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.24.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.25.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.25.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.26.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.26.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.28.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.28.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.29.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.29.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.30.linear_attn.in_proj_b": {
+      "bits": 8
+    },
+    "model.language_model.layers.30.linear_attn.in_proj_a": {
+      "bits": 8
+    },
+    "model.language_model.layers.0.linear_attn.out_proj": {
+      "bits": 8
+    },
+    "model.language_model.layers.1.linear_attn.out_proj": {
+      "bits": 8
+    },
+    "model.language_model.layers.2.linear_attn.out_proj": {
+      "bits": 8
+    },
+    "model.language_model.layers.2.mlp.down_proj": {
+      "bits": 8
+    },
+    "model.language_model.layers.3.self_attn.o_proj": {
+      "bits": 8
+    },
+    "model.language_model.layers.7.self_attn.o_proj": {
+      "bits": 8
+    },
+    "model.language_model.layers.11.self_attn.o_proj": {
+      "bits": 8
+    }
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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,
+  "local_files_only": false,
+  "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": "<|endoftext|>",
+  "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": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}