Duplicate from Tesslate/OmniCoder-9B

Co-authored-by: Manav Majumdar <smirki@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,227 @@
+---
+library_name: transformers
+base_model: Qwen/Qwen3.5-9B
+tags:
+  - qwen3.5
+  - code
+  - agent
+  - sft
+  - omnicoder
+  - tesslate
+license: apache-2.0
+language:
+  - en
+pipeline_tag: text-generation
+model-index:
+  - name: OmniCoder-9B
+    results:
+      - task:
+          type: text-generation
+        dataset:
+          name: AIME 2025
+          type: custom
+        metrics:
+          - name: pass@5
+            type: accuracy
+            value: 90.0
+      - task:
+          type: text-generation
+        dataset:
+          name: GPQA Diamond
+          type: custom
+        metrics:
+          - name: pass@1
+            type: accuracy
+            value: 83.8
+          - name: pass@3
+            type: accuracy
+            value: 86.4
+      - task:
+          type: text-generation
+        dataset:
+          name: Terminal-Bench 2.0
+          type: custom
+        metrics:
+          - name: Pass Rate
+            type: accuracy
+            value: 28.1
+---
+
+<div align="center">
+
+<img src="omnicoder-banner.png" alt="OmniCoder" width="720">
+
+# OmniCoder-9B
+
+### A 9B coding agent fine-tuned on 425K agentic trajectories.
+
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Base Model](https://img.shields.io/badge/Base-Qwen3.5--9B-purple)](https://huggingface.co/Qwen/Qwen3.5-9B)
+[![GGUF](https://img.shields.io/badge/GGUF-Available-green)](https://huggingface.co/Tesslate/OmniCoder-9B-GGUF)
+
+!! 3/12/26 Update -> [Install For Your Coding Agents](https://tesslate.com/install#omnicoder)
+
+[Get Started](#quickstart) | [Benchmarks](#benchmarks) | [GGUF Downloads](https://huggingface.co/Tesslate/OmniCoder-9B-GGUF)
+
+---
+
+</div>
+
+## Overview
+
+**OmniCoder-9B** is a 9-billion parameter coding agent model built by [Tesslate](https://tesslate.com), fine-tuned on top of [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B)'s hybrid architecture (Gated Delta Networks interleaved with standard attention). It was trained on **425,000+ curated agentic coding trajectories** spanning real-world software engineering tasks, tool use, terminal operations, and multi-step reasoning.
+
+The training data was specifically built from **Claude Opus 4.6 agentic and coding reasoning traces**, targeting scaffolding patterns from Claude Code, OpenCode, Codex, and Droid. The dataset includes successful trajectories from models like Claude Opus 4.6, GPT-5.4, GPT-5.3-Codex, and Gemini 3.1 Pro.
+
+The model shows strong agentic behavior: it recovers from errors (read-before-write), responds to LSP diagnostics, and uses proper edit diffs instead of full rewrites. These patterns were learned directly from the real-world agent trajectories it was trained on.
+
+### Key Features
+
+- **Trained on Frontier Agent Traces** : Built from Claude Opus 4.6, GPT-5.3-Codex, GPT-5.4, and Gemini 3.1 Pro agentic coding trajectories across Claude Code, OpenCode, Codex, and Droid scaffolding
+- **Hybrid Architecture** : Inherits Qwen3.5's Gated Delta Networks interleaved with standard attention for efficient long-context processing
+- **262K Native Context** : Full 262,144 token context window, extensible to 1M+
+- **Error Recovery** : Learns read-before-write patterns, responds to LSP diagnostics, and applies minimal edit diffs instead of full rewrites
+- **Thinking Mode** : Supports `<think>...</think>` reasoning chains for complex problem decomposition
+- **Apache 2.0** : Fully open weights, no restrictions
+
+---
+
+## Benchmarks
+
+<div align="center">
+
+| Benchmark | **OmniCoder-9B** | Qwen3.5-9B | Qwen3-Next-80B | GPT-OSS-120B | GPT-OSS-20B | GLM-4.7-Flash | GLM 4.7 | Claude Haiku 4.5 |
+|:---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| **AIME 2025** (pass@5) | 90 | | | | 91.7 | 91.6 | | |
+| **GPQA Diamond** (pass@1) | **83.8** | 81.7 | 77.2 | 80.1 | 71.5 | | | 73 |
+| **GPQA Diamond** (pass@3) | **86.4** | | | | | | | |
+| **Terminal-Bench 2.0** | **23.6** | 14.6 | | | | | 33.4 | 27 |
+
+</div>
+
+- **GPQA Diamond pass@1: 83.8%** (166/198). +2.1 points over the Qwen3.5-9B base model (81.7). At pass@3: **86.4** (171/198).
+- **AIME 2025 pass@5: 90%** (27/30).
+- **Terminal-Bench 2.0: 23.6%** (21/89). +8.99 points (+61% improvement) over the Qwen3.5-9B base model (14.6%, 13/89).
+
+---
+
+## Quickstart
+
+### Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Tesslate/OmniCoder-9B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
+
+messages = [
+    {"role": "system", "content": "You are a helpful coding assistant."},
+    {"role": "user", "content": "Write a Python function to find the longest common subsequence of two strings."},
+]
+
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.6, top_p=0.95, top_k=20)
+print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
+```
+
+### vLLM
+
+```bash
+vllm serve Tesslate/OmniCoder-9B --tensor-parallel-size 1 --max-model-len 65536
+```
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="token")
+response = client.chat.completions.create(
+    model="Tesslate/OmniCoder-9B",
+    messages=[{"role": "user", "content": "Explain the difference between a mutex and a semaphore."}],
+    temperature=0.6,
+)
+print(response.choices[0].message.content)
+```
+
+### llama.cpp (GGUF)
+
+```bash
+llama-cli --hf-repo Tesslate/OmniCoder-9B-GGUF --hf-file omnicoder-9b-q4_k_m.gguf -p "Your prompt" -c 8192
+```
+
+All quantizations: [Tesslate/OmniCoder-9B-GGUF](https://huggingface.co/Tesslate/OmniCoder-9B-GGUF)
+
+---
+
+## Training Details
+
+| | |
+|:---|:---|
+| **Base Model** | [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) |
+| **Method** | LoRA SFT (r=64, alpha=32) |
+| **Dataset** | 425K agentic trajectories from 5 sources |
+| **Packing** | Sample packing with 99.35% efficiency |
+| **Hardware** | 4x NVIDIA H200 (DDP) |
+| **Framework** | Axolotl |
+| **Precision** | bf16 |
+| **Optimizer** | AdamW (lr=2e-4, cosine schedule) |
+
+---
+
+## Architecture
+
+OmniCoder inherits Qwen3.5-9B's hybrid architecture:
+
+- **Gated Delta Networks** : Linear attention layers interleaved with standard attention for efficient long-range dependencies
+- **VLM Backbone** : Built on `Qwen3_5ForConditionalGeneration`
+
+---
+
+## Recommended Sampling Parameters
+
+| Parameter | Value |
+|:---|:---|
+| Temperature | 0.6 |
+| Top-P | 0.95 |
+| Top-K | 20 |
+| Presence Penalty | 0.0 |
+
+For agentic / tool-calling tasks, consider lower temperature (0.2-0.4) for more deterministic behavior.
+
+---
+
+## Limitations
+
+- Performance on non-English tasks has not been extensively evaluated
+- Tool-calling format is flexible but works best with the scaffolding patterns seen in training
+
+---
+
+## Acknowledgments
+
+Special thanks to the [Axolotl](https://github.com/axolotl-ai-cloud/axolotl) team and the discussion in [axolotl#3453](https://github.com/axolotl-ai-cloud/axolotl/issues/3453) for helping get Qwen3.5 packing support working.
+
+---
+
+## Citation
+
+```bibtex
+@misc{omnicoder2025,
+  title={OmniCoder-9B: A Frontier Open Coding Agent},
+  author={Tesslate},
+  year={2025},
+  url={https://huggingface.co/Tesslate/OmniCoder-9B}
+}
+```
+
+---
+
+<div align="center">
+
+**Built by [Tesslate](https://tesslate.com)**
+
+</div>

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 +1,109 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "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,
+    "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": [],
+    "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,
+    "model_type": "qwen3_5_text"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0.dev0",
+  "unsloth_fixed": true,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5",
+    "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 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "transformers_version": "5.3.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4fca6821fe35b46e684ab88217ec25cdbfcdf9fa208c01110be95a200fcc33b
+size 18819722360

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "patch_size": 16,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Qwen3VLProcessor",
+  "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "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": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "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"
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "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": 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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}