Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,410 @@
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- Qwen/Qwen3-Next-80B-A3B-Instruct
+---
+
+# Qwen3-Next-80B-A3B-Instruct AWQ - INT4
+
+## Model Details
+
+### Quantization Details
+
+- **Quantization Method:** cyankiwi AWQ v1.0
+- **Bits:** 4
+- **Group Size:** 32
+- **Calibration Dataset:** [nvidia/Llama-Nemotron-Post-Training-Dataset](https://huggingface.co/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset)
+- **Quantization Tool:** [llm-compressor](https://github.com/vllm-project/llm-compressor)
+
+### Memory Usage
+
+| **Type** | **Qwen3-Next-80B-A3B-Instruct** | **Qwen3-Next-80B-A3B-Instruct-AWQ-4bit** |
+|:---------------:|:----------------:|:----------------:|
+| **Memory Size** | 151.5 GB | 45.9 GB | 
+
+### Evaluations
+
+| **Benchmarks** | **Qwen3-Next-80B-A3B-Instruct** | **Qwen3-Next-80B-A3B-Instruct-AWQ-4bit** |
+|:---------------:|:----------------:|:----------------:|
+| **Perplexity** | 1.48256 | 1.48602 | 
+| **GPQA Diamond** | 74.2 | 73.7 | 
+| **AIME25** | 70.0 | 70.0 | 
+
+- **Evaluation Context Length:** 16384
+
+## Inference
+
+### Prerequisite
+
+```bash
+VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
+```
+
+### Basic Usage
+
+```bash
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit \
+    --port 8000 \
+    --tensor-parallel-size 4 \
+    --max-model-len 262144 \
+    --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
+```
+
+## Additional Information
+
+### Changelog
+
+- **v1.0.0** - Add MTP layers.
+- **v0.1.0** - Initial quantized release
+
+### Authors
+
+- **Name:** Ton Cao
+- **Contacts:** ton@cyan.kiwi
+
+# Qwen3-Next-80B-A3B-Instruct
+<a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). 
+We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. 
+We call this next-generation foundation models **Qwen3-Next**.
+
+## Highlights
+
+**Qwen3-Next-80B-A3B** is the first installment in the Qwen3-Next series and features the following key enchancements:
+- **Hybrid Attention**: Replaces standard attention with the combination of **Gated DeltaNet** and **Gated Attention**, enabling efficient context modeling for ultra-long context length.
+- **High-Sparsity Mixture-of-Experts (MoE)**: Achieves an extreme low activation ratio in MoE layers, drastically reducing FLOPs per token while preserving model capacity. 
+- **Stability Optimizations**: Includes techniques such as **zero-centered and weight-decayed layernorm**, and other stabilizing enhancements for robust pre-training and post-training.  
+- **Multi-Token Prediction (MTP)**: Boosts pretraining model performance and accelerates inference.
+
+We are seeing strong performance in terms of both parameter efficiency and inference speed for Qwen3-Next-80B-A3B:
+- Qwen3-Next-80B-A3B-Base outperforms Qwen3-32B-Base on downstream tasks with 10% of the total training cost and with 10 times inference throughput for context over 32K tokens.
+- Qwen3-Next-80B-A3B-Instruct performs on par with Qwen3-235B-A22B-Instruct-2507 on certain benchmarks, while demonstrating significant advantages in handling ultra-long-context tasks up to 256K tokens.
+
+![Qwen3-Next-80B-A3B-Instruct Benchmark Comparison](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-Next/Qwen3-Next-80B-A3B-Instruct.001.jpeg)
+
+For more details, please refer to our blog post [Qwen3-Next](https://qwenlm.github.io/blog/qwen3_next/).
+
+## Model Overview
+
+> [!Note]
+> **Qwen3-Next-80B-A3B-Instruct** supports only instruct (non-thinking) mode and does not generate ``<think></think>`` blocks in its output.
+
+**Qwen3-Next-80B-A3B-Instruct** has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining (15T tokens) & Post-training
+- Number of Parameters: 80B in total and 3B activated
+- Number of Paramaters (Non-Embedding): 79B
+- Number of Layers: 48
+- Hidden Dimension: 2048
+- Hybrid Layout: 12 \* (3 \* (Gated DeltaNet -> MoE) -> (Gated Attention -> MoE))
+- Gated Attention:
+  - Number of Attention Heads: 16 for Q and 2 for KV
+  - Head Dimension: 256
+  - Rotary Position Embedding Dimension: 64
+- Gated DeltaNet:
+  - Number of Linear Attention Heads: 32 for V and 16 for QK
+  - Head Dimension: 128
+- Mixture of Experts:
+  - Number of Experts: 512
+  - Number of Activated Experts: 10
+  - Number of Shared Experts: 1
+  - Expert Intermediate Dimension: 512
+- Context Length: 262,144 natively and extensible up to 1,010,000 tokens
+
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-Next/model_architecture.png" height="384px" title="Qwen3-Next Model Architecture" />
+
+
+## Performance
+
+|  | Qwen3-30B-A3B-Instruct-2507 | Qwen3-32B Non-Thinking | Qwen3-235B-A22B-Instruct-2507 | Qwen3-Next-80B-A3B-Instruct |
+|--- | --- | --- | --- | --- |
+| **Knowledge** | | | | |
+| MMLU-Pro | 78.4 | 71.9 | **83.0** | 80.6 |
+| MMLU-Redux | 89.3 | 85.7 | **93.1** | 90.9 |
+| GPQA | 70.4 | 54.6 | **77.5** | 72.9 |
+| SuperGPQA | 53.4 | 43.2 | **62.6** | 58.8 |
+| **Reasoning** | | | | |
+| AIME25 | 61.3 | 20.2 | **70.3** | 69.5 |
+| HMMT25 | 43.0 | 9.8 | **55.4** | 54.1 |
+| LiveBench 20241125 | 69.0 | 59.8 | 75.4 | **75.8** |
+| **Coding** | | | | |
+| LiveCodeBench v6 (25.02-25.05) | 43.2 | 29.1 | 51.8 | **56.6** |
+| MultiPL-E | 83.8 | 76.9 | **87.9** | 87.8 |
+| Aider-Polyglot | 35.6 | 40.0 | **57.3** | 49.8 |
+| **Alignment** | | | | |
+| IFEval | 84.7 | 83.2 | **88.7** | 87.6 |
+| Arena-Hard v2* | 69.0 | 34.1 | 79.2 | **82.7** |
+| Creative Writing v3 | 86.0 | 78.3 | **87.5** | 85.3 |
+| WritingBench | 85.5 | 75.4 | 85.2 | **87.3** |
+| **Agent** | | | | |
+| BFCL-v3 | 65.1 | 63.0 | **70.9** | 70.3 |
+| TAU1-Retail | 59.1 | 40.1 | **71.3** | 60.9 |
+| TAU1-Airline | 40.0 | 17.0 | **44.0** | 44.0 |
+| TAU2-Retail | 57.0 | 48.8 | **74.6** | 57.3 |
+| TAU2-Airline | 38.0 | 24.0 | **50.0** | 45.5 |
+| TAU2-Telecom | 12.3 | 24.6 | **32.5** | 13.2 |
+| **Multilingualism** | | | | |
+| MultiIF | 67.9 | 70.7 | **77.5** | 75.8 |
+| MMLU-ProX | 72.0 | 69.3 | **79.4** | 76.7 |
+| INCLUDE | 71.9 | 70.9 | **79.5** | 78.9 |
+| PolyMATH | 43.1 | 22.5 | **50.2** | 45.9 |
+
+*: For reproducibility, we report the win rates evaluated by GPT-4.1.
+
+## Quickstart
+
+The code for Qwen3-Next has been merged into the main branch of Hugging Face `transformers`.
+
+```shell
+pip install git+https://github.com/huggingface/transformers.git@main
+```
+
+With earlier versions, you will encounter the following error:
+```
+KeyError: 'qwen3_next'
+```
+
+The following contains a code snippet illustrating how to use the model generate content based on given inputs. 
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen3-Next-80B-A3B-Instruct"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    dtype="auto",
+    device_map="auto",
+)
+
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt},
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=16384,
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+content = tokenizer.decode(output_ids, skip_special_tokens=True)
+
+print("content:", content)
+```
+
+> [!Note]
+> Multi-Token Prediction (MTP) is not generally available in Hugging Face Transformers.
+
+> [!Note]
+> The efficiency or throughput improvement depends highly on the implementation.
+> It is recommended to adopt a dedicated inference framework, e.g., SGLang and vLLM, for inference tasks.
+
+> [!Tip]
+> Depending on the inference settings, you may observe better efficiency with [`flash-linear-attention`](https://github.com/fla-org/flash-linear-attention#installation) and [`causal-conv1d`](https://github.com/Dao-AILab/causal-conv1d).
+> See the above links for detailed instructions and requirements.
+
+
+## Deployment
+
+For deployment, you can use the latest `sglang` or `vllm` to create an OpenAI-compatible API endpoint.
+
+### SGLang
+
+[SGLang](https://github.com/sgl-project/sglang) is a fast serving framework for large language models and vision language models.
+SGLang could be used to launch a server with OpenAI-compatible API service. 
+
+SGLang has supported Qwen3-Next in its `main` branch, which can be installed from source:
+```shell
+pip install 'sglang[all] @ git+https://github.com/sgl-project/sglang.git@main#subdirectory=python'
+```
+
+The following command can be used to create an API endpoint at `http://localhost:30000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
+```shell
+SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8
+```
+
+The following command is recommended for MTP with the rest settings the same as above:
+```shell
+SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
+```
+
+> [!Note]
+> The environment variable `SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1` is required at the moment.
+
+> [!Note]
+> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fail to start.
+
+### vLLM
+
+[vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
+vLLM could be used to launch a server with OpenAI-compatible API service. 
+
+vLLM has supported Qwen3-Next in its `main` branch, which can be installed from source:
+```shell
+pip install git+https://github.com/vllm-project/vllm.git
+```
+
+The following command can be used to create an API endpoint at `http://localhost:8000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
+```shell
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144
+```
+
+The following command is recommended for MTP with the rest settings the same as above:
+```shell
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
+```
+
+> [!Note]
+> The environment variable `VLLM_ALLOW_LONG_MAX_MODEL_LEN=1` is required at the moment.
+
+> [!Note]
+> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fail to start.
+
+## Agentic Use
+
+Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
+
+To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
+```python
+from qwen_agent.agents import Assistant
+
+# Define LLM
+llm_cfg = {
+    'model': 'Qwen3-Next-80B-A3B-Instruct',
+
+    # Use a custom endpoint compatible with OpenAI API:
+    'model_server': 'http://localhost:8000/v1',  # api_base
+    'api_key': 'EMPTY',
+}
+
+# Define Tools
+tools = [
+    {'mcpServers': {  # You can specify the MCP configuration file
+            'time': {
+                'command': 'uvx',
+                'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
+            },
+            "fetch": {
+                "command": "uvx",
+                "args": ["mcp-server-fetch"]
+            }
+        }
+    },
+  'code_interpreter',  # Built-in tools
+]
+
+# Define Agent
+bot = Assistant(llm=llm_cfg, function_list=tools)
+
+# Streaming generation
+messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
+for responses in bot.run(messages=messages):
+    pass
+print(responses)
+```
+
+
+## Processing Ultra-Long Texts
+
+Qwen3-Next natively supports context lengths of up to 262,144 tokens. 
+For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. 
+We have validated the model's performance on context lengths of up to 1 million tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.
+
+YaRN is currently supported by several inference frameworks, e.g., `transformers`, `vllm` and `sglang`. 
+In general, there are two approaches to enabling YaRN for supported frameworks:
+
+- Modifying the model files:
+  In the `config.json` file, add the `rope_scaling` fields:
+    ```json
+    {
+        ...,
+        "rope_scaling": {
+            "rope_type": "yarn",
+            "factor": 4.0,
+            "original_max_position_embeddings": 262144
+        }
+    }
+    ```
+
+- Passing command line arguments:
+
+  For `vllm`, you can use
+    ```shell
+    VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve ... --rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":262144}' --max-model-len 1010000  
+    ```
+
+  For `sglang`, you can use
+    ```shell
+    SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":262144}}' --context-length 1010000
+    ```
+
+> [!NOTE]
+> All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts.**
+> We advise adding the `rope_scaling` configuration only when processing long contexts is required. 
+> It is also recommended to modify the `factor` as needed. For example, if the typical context length for your application is 524,288 tokens, it would be better to set `factor` as 2.0. 
+
+#### Long-Context Performance
+
+We test the model on an 1M version of the [RULER](https://arxiv.org/abs/2404.06654) benchmark.
+
+| Model Name                                  | Acc avg | 4k   | 8k   | 16k  | 32k  | 64k  | 96k  | 128k | 192k | 256k | 384k | 512k | 640k | 768k | 896k | 1000k |
+|---------------------------------------------|---------|------|------|------|------|------|------|------|------|------|------|------|------|------|------|-------|
+| Qwen3-30B-A3B-Instruct-2507                 | 86.8    | 98.0 | 96.7 | 96.9 | 97.2 | 93.4 | 91.0 | 89.1 | 89.8 | 82.5 | 83.6 | 78.4 | 79.7 | 77.6 | 75.7 | 72.8  |
+| Qwen3-235B-A22B-Instruct-2507               | 92.5    | 98.5 | 97.6 | 96.9 | 97.3 | 95.8 | 94.9 | 93.9 | 94.5 | 91.0 | 92.2 | 90.9 | 87.8 | 84.8 | 86.5 | 84.5  |
+| Qwen3-Next-80B-A3B-Instruct                 | 91.8    | 98.5 | 99.0 | 98.0 | 98.7 | 97.6 | 95.0 | 96.0 | 94.0 | 93.5 | 91.7 | 86.9 | 85.5 | 81.7 | 80.3 | 80.3  |
+
+* Qwen3-Next are evaluated with YaRN enabled. Qwen3-2507 models are evaluated with Dual Chunk Attention enabled.
+* Since the evaluation is time-consuming, we use 260 samples for each length (13 sub-tasks, 20 samples for each).
+
+## Best Practices
+
+To achieve optimal performance, we recommend the following settings:
+
+1. **Sampling Parameters**:
+   - We suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
+   - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
+
+2. **Adequate Output Length**: We recommend using an output length of 16,384 tokens for most queries, which is adequate for instruct models.
+
+3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
+   - **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
+   - **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
+
+### Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report}, 
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}, 
+}
+
+@article{qwen2.5-1m,
+      title={Qwen2.5-1M Technical Report}, 
+      author={An Yang and Bowen Yu and Chengyuan Li and Dayiheng Liu and Fei Huang and Haoyan Huang and Jiandong Jiang and Jianhong Tu and Jianwei Zhang and Jingren Zhou and Junyang Lin and Kai Dang and Kexin Yang and Le Yu and Mei Li and Minmin Sun and Qin Zhu and Rui Men and Tao He and Weijia Xu and Wenbiao Yin and Wenyuan Yu and Xiafei Qiu and Xingzhang Ren and Xinlong Yang and Yong Li and Zhiying Xu and Zipeng Zhang},
+      journal={arXiv preprint arXiv:2501.15383},
+      year={2025}
+}
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,61 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,535 @@
+{
+  "architectures": [
+    "Qwen3NextForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_next",
+  "moe_intermediate_size": 512,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 512,
+  "num_experts_per_tok": 10,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "partial_rotary_factor": 0.25,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 4,
+          "observer": "mse",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.layers.0.linear_attn.in_proj_qkvz",
+      "model.layers.0.linear_attn.in_proj_ba",
+      "model.layers.0.linear_attn.out_proj",
+      "model.layers.0.mlp.gate",
+      "model.layers.0.mlp.shared_expert.gate_proj",
+      "model.layers.0.mlp.shared_expert.up_proj",
+      "model.layers.0.mlp.shared_expert.down_proj",
+      "model.layers.0.mlp.shared_expert_gate",
+      "model.layers.1.linear_attn.in_proj_qkvz",
+      "model.layers.1.linear_attn.in_proj_ba",
+      "model.layers.1.linear_attn.out_proj",
+      "model.layers.1.mlp.gate",
+      "model.layers.1.mlp.shared_expert.gate_proj",
+      "model.layers.1.mlp.shared_expert.up_proj",
+      "model.layers.1.mlp.shared_expert.down_proj",
+      "model.layers.1.mlp.shared_expert_gate",
+      "model.layers.2.linear_attn.in_proj_qkvz",
+      "model.layers.2.linear_attn.in_proj_ba",
+      "model.layers.2.linear_attn.out_proj",
+      "model.layers.2.mlp.gate",
+      "model.layers.2.mlp.shared_expert.gate_proj",
+      "model.layers.2.mlp.shared_expert.up_proj",
+      "model.layers.2.mlp.shared_expert.down_proj",
+      "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.3.self_attn.q_proj",
+      "model.layers.3.self_attn.k_proj",
+      "model.layers.3.self_attn.v_proj",
+      "model.layers.3.self_attn.o_proj",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.shared_expert.gate_proj",
+      "model.layers.3.mlp.shared_expert.up_proj",
+      "model.layers.3.mlp.shared_expert.down_proj",
+      "model.layers.3.mlp.shared_expert_gate",
+      "model.layers.4.linear_attn.in_proj_qkvz",
+      "model.layers.4.linear_attn.in_proj_ba",
+      "model.layers.4.linear_attn.out_proj",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.mlp.shared_expert.gate_proj",
+      "model.layers.4.mlp.shared_expert.up_proj",
+      "model.layers.4.mlp.shared_expert.down_proj",
+      "model.layers.4.mlp.shared_expert_gate",
+      "model.layers.5.linear_attn.in_proj_qkvz",
+      "model.layers.5.linear_attn.in_proj_ba",
+      "model.layers.5.linear_attn.out_proj",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.mlp.shared_expert.gate_proj",
+      "model.layers.5.mlp.shared_expert.up_proj",
+      "model.layers.5.mlp.shared_expert.down_proj",
+      "model.layers.5.mlp.shared_expert_gate",
+      "model.layers.6.linear_attn.in_proj_qkvz",
+      "model.layers.6.linear_attn.in_proj_ba",
+      "model.layers.6.linear_attn.out_proj",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.shared_expert.gate_proj",
+      "model.layers.6.mlp.shared_expert.up_proj",
+      "model.layers.6.mlp.shared_expert.down_proj",
+      "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.7.self_attn.q_proj",
+      "model.layers.7.self_attn.k_proj",
+      "model.layers.7.self_attn.v_proj",
+      "model.layers.7.self_attn.o_proj",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.mlp.shared_expert.gate_proj",
+      "model.layers.7.mlp.shared_expert.up_proj",
+      "model.layers.7.mlp.shared_expert.down_proj",
+      "model.layers.7.mlp.shared_expert_gate",
+      "model.layers.8.linear_attn.in_proj_qkvz",
+      "model.layers.8.linear_attn.in_proj_ba",
+      "model.layers.8.linear_attn.out_proj",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.mlp.shared_expert.gate_proj",
+      "model.layers.8.mlp.shared_expert.up_proj",
+      "model.layers.8.mlp.shared_expert.down_proj",
+      "model.layers.8.mlp.shared_expert_gate",
+      "model.layers.9.linear_attn.in_proj_qkvz",
+      "model.layers.9.linear_attn.in_proj_ba",
+      "model.layers.9.linear_attn.out_proj",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.shared_expert.gate_proj",
+      "model.layers.9.mlp.shared_expert.up_proj",
+      "model.layers.9.mlp.shared_expert.down_proj",
+      "model.layers.9.mlp.shared_expert_gate",
+      "model.layers.10.linear_attn.in_proj_qkvz",
+      "model.layers.10.linear_attn.in_proj_ba",
+      "model.layers.10.linear_attn.out_proj",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.mlp.shared_expert.gate_proj",
+      "model.layers.10.mlp.shared_expert.up_proj",
+      "model.layers.10.mlp.shared_expert.down_proj",
+      "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.11.self_attn.q_proj",
+      "model.layers.11.self_attn.k_proj",
+      "model.layers.11.self_attn.v_proj",
+      "model.layers.11.self_attn.o_proj",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.mlp.shared_expert.gate_proj",
+      "model.layers.11.mlp.shared_expert.up_proj",
+      "model.layers.11.mlp.shared_expert.down_proj",
+      "model.layers.11.mlp.shared_expert_gate",
+      "model.layers.12.linear_attn.in_proj_qkvz",
+      "model.layers.12.linear_attn.in_proj_ba",
+      "model.layers.12.linear_attn.out_proj",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.shared_expert.gate_proj",
+      "model.layers.12.mlp.shared_expert.up_proj",
+      "model.layers.12.mlp.shared_expert.down_proj",
+      "model.layers.12.mlp.shared_expert_gate",
+      "model.layers.13.linear_attn.in_proj_qkvz",
+      "model.layers.13.linear_attn.in_proj_ba",
+      "model.layers.13.linear_attn.out_proj",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.mlp.shared_expert.gate_proj",
+      "model.layers.13.mlp.shared_expert.up_proj",
+      "model.layers.13.mlp.shared_expert.down_proj",
+      "model.layers.13.mlp.shared_expert_gate",
+      "model.layers.14.linear_attn.in_proj_qkvz",
+      "model.layers.14.linear_attn.in_proj_ba",
+      "model.layers.14.linear_attn.out_proj",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.mlp.shared_expert.gate_proj",
+      "model.layers.14.mlp.shared_expert.up_proj",
+      "model.layers.14.mlp.shared_expert.down_proj",
+      "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.15.self_attn.q_proj",
+      "model.layers.15.self_attn.k_proj",
+      "model.layers.15.self_attn.v_proj",
+      "model.layers.15.self_attn.o_proj",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.shared_expert.gate_proj",
+      "model.layers.15.mlp.shared_expert.up_proj",
+      "model.layers.15.mlp.shared_expert.down_proj",
+      "model.layers.15.mlp.shared_expert_gate",
+      "model.layers.16.linear_attn.in_proj_qkvz",
+      "model.layers.16.linear_attn.in_proj_ba",
+      "model.layers.16.linear_attn.out_proj",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.mlp.shared_expert.gate_proj",
+      "model.layers.16.mlp.shared_expert.up_proj",
+      "model.layers.16.mlp.shared_expert.down_proj",
+      "model.layers.16.mlp.shared_expert_gate",
+      "model.layers.17.linear_attn.in_proj_qkvz",
+      "model.layers.17.linear_attn.in_proj_ba",
+      "model.layers.17.linear_attn.out_proj",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.mlp.shared_expert.gate_proj",
+      "model.layers.17.mlp.shared_expert.up_proj",
+      "model.layers.17.mlp.shared_expert.down_proj",
+      "model.layers.17.mlp.shared_expert_gate",
+      "model.layers.18.linear_attn.in_proj_qkvz",
+      "model.layers.18.linear_attn.in_proj_ba",
+      "model.layers.18.linear_attn.out_proj",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.shared_expert.gate_proj",
+      "model.layers.18.mlp.shared_expert.up_proj",
+      "model.layers.18.mlp.shared_expert.down_proj",
+      "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.19.self_attn.q_proj",
+      "model.layers.19.self_attn.k_proj",
+      "model.layers.19.self_attn.v_proj",
+      "model.layers.19.self_attn.o_proj",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.mlp.shared_expert.gate_proj",
+      "model.layers.19.mlp.shared_expert.up_proj",
+      "model.layers.19.mlp.shared_expert.down_proj",
+      "model.layers.19.mlp.shared_expert_gate",
+      "model.layers.20.linear_attn.in_proj_qkvz",
+      "model.layers.20.linear_attn.in_proj_ba",
+      "model.layers.20.linear_attn.out_proj",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.mlp.shared_expert.gate_proj",
+      "model.layers.20.mlp.shared_expert.up_proj",
+      "model.layers.20.mlp.shared_expert.down_proj",
+      "model.layers.20.mlp.shared_expert_gate",
+      "model.layers.21.linear_attn.in_proj_qkvz",
+      "model.layers.21.linear_attn.in_proj_ba",
+      "model.layers.21.linear_attn.out_proj",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.shared_expert.gate_proj",
+      "model.layers.21.mlp.shared_expert.up_proj",
+      "model.layers.21.mlp.shared_expert.down_proj",
+      "model.layers.21.mlp.shared_expert_gate",
+      "model.layers.22.linear_attn.in_proj_qkvz",
+      "model.layers.22.linear_attn.in_proj_ba",
+      "model.layers.22.linear_attn.out_proj",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.mlp.shared_expert.gate_proj",
+      "model.layers.22.mlp.shared_expert.up_proj",
+      "model.layers.22.mlp.shared_expert.down_proj",
+      "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.23.self_attn.q_proj",
+      "model.layers.23.self_attn.k_proj",
+      "model.layers.23.self_attn.v_proj",
+      "model.layers.23.self_attn.o_proj",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.shared_expert.gate_proj",
+      "model.layers.23.mlp.shared_expert.up_proj",
+      "model.layers.23.mlp.shared_expert.down_proj",
+      "model.layers.23.mlp.shared_expert_gate",
+      "model.layers.24.linear_attn.in_proj_qkvz",
+      "model.layers.24.linear_attn.in_proj_ba",
+      "model.layers.24.linear_attn.out_proj",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.mlp.shared_expert.gate_proj",
+      "model.layers.24.mlp.shared_expert.up_proj",
+      "model.layers.24.mlp.shared_expert.down_proj",
+      "model.layers.24.mlp.shared_expert_gate",
+      "model.layers.25.linear_attn.in_proj_qkvz",
+      "model.layers.25.linear_attn.in_proj_ba",
+      "model.layers.25.linear_attn.out_proj",
+      "model.layers.25.mlp.gate",
+      "model.layers.25.mlp.shared_expert.gate_proj",
+      "model.layers.25.mlp.shared_expert.up_proj",
+      "model.layers.25.mlp.shared_expert.down_proj",
+      "model.layers.25.mlp.shared_expert_gate",
+      "model.layers.26.linear_attn.in_proj_qkvz",
+      "model.layers.26.linear_attn.in_proj_ba",
+      "model.layers.26.linear_attn.out_proj",
+      "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.shared_expert.gate_proj",
+      "model.layers.26.mlp.shared_expert.up_proj",
+      "model.layers.26.mlp.shared_expert.down_proj",
+      "model.layers.26.mlp.shared_expert_gate",
+      "model.layers.27.self_attn.q_proj",
+      "model.layers.27.self_attn.k_proj",
+      "model.layers.27.self_attn.v_proj",
+      "model.layers.27.self_attn.o_proj",
+      "model.layers.27.mlp.gate",
+      "model.layers.27.mlp.shared_expert.gate_proj",
+      "model.layers.27.mlp.shared_expert.up_proj",
+      "model.layers.27.mlp.shared_expert.down_proj",
+      "model.layers.27.mlp.shared_expert_gate",
+      "model.layers.28.linear_attn.in_proj_qkvz",
+      "model.layers.28.linear_attn.in_proj_ba",
+      "model.layers.28.linear_attn.out_proj",
+      "model.layers.28.mlp.gate",
+      "model.layers.28.mlp.shared_expert.gate_proj",
+      "model.layers.28.mlp.shared_expert.up_proj",
+      "model.layers.28.mlp.shared_expert.down_proj",
+      "model.layers.28.mlp.shared_expert_gate",
+      "model.layers.29.linear_attn.in_proj_qkvz",
+      "model.layers.29.linear_attn.in_proj_ba",
+      "model.layers.29.linear_attn.out_proj",
+      "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.shared_expert.gate_proj",
+      "model.layers.29.mlp.shared_expert.up_proj",
+      "model.layers.29.mlp.shared_expert.down_proj",
+      "model.layers.29.mlp.shared_expert_gate",
+      "model.layers.30.linear_attn.in_proj_qkvz",
+      "model.layers.30.linear_attn.in_proj_ba",
+      "model.layers.30.linear_attn.out_proj",
+      "model.layers.30.mlp.gate",
+      "model.layers.30.mlp.shared_expert.gate_proj",
+      "model.layers.30.mlp.shared_expert.up_proj",
+      "model.layers.30.mlp.shared_expert.down_proj",
+      "model.layers.30.mlp.shared_expert_gate",
+      "model.layers.31.self_attn.q_proj",
+      "model.layers.31.self_attn.k_proj",
+      "model.layers.31.self_attn.v_proj",
+      "model.layers.31.self_attn.o_proj",
+      "model.layers.31.mlp.gate",
+      "model.layers.31.mlp.shared_expert.gate_proj",
+      "model.layers.31.mlp.shared_expert.up_proj",
+      "model.layers.31.mlp.shared_expert.down_proj",
+      "model.layers.31.mlp.shared_expert_gate",
+      "model.layers.32.linear_attn.in_proj_qkvz",
+      "model.layers.32.linear_attn.in_proj_ba",
+      "model.layers.32.linear_attn.out_proj",
+      "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.shared_expert.gate_proj",
+      "model.layers.32.mlp.shared_expert.up_proj",
+      "model.layers.32.mlp.shared_expert.down_proj",
+      "model.layers.32.mlp.shared_expert_gate",
+      "model.layers.33.linear_attn.in_proj_qkvz",
+      "model.layers.33.linear_attn.in_proj_ba",
+      "model.layers.33.linear_attn.out_proj",
+      "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.shared_expert.gate_proj",
+      "model.layers.33.mlp.shared_expert.up_proj",
+      "model.layers.33.mlp.shared_expert.down_proj",
+      "model.layers.33.mlp.shared_expert_gate",
+      "model.layers.34.linear_attn.in_proj_qkvz",
+      "model.layers.34.linear_attn.in_proj_ba",
+      "model.layers.34.linear_attn.out_proj",
+      "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.shared_expert.gate_proj",
+      "model.layers.34.mlp.shared_expert.up_proj",
+      "model.layers.34.mlp.shared_expert.down_proj",
+      "model.layers.34.mlp.shared_expert_gate",
+      "model.layers.35.self_attn.q_proj",
+      "model.layers.35.self_attn.k_proj",
+      "model.layers.35.self_attn.v_proj",
+      "model.layers.35.self_attn.o_proj",
+      "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.shared_expert.gate_proj",
+      "model.layers.35.mlp.shared_expert.up_proj",
+      "model.layers.35.mlp.shared_expert.down_proj",
+      "model.layers.35.mlp.shared_expert_gate",
+      "model.layers.36.linear_attn.in_proj_qkvz",
+      "model.layers.36.linear_attn.in_proj_ba",
+      "model.layers.36.linear_attn.out_proj",
+      "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.shared_expert.gate_proj",
+      "model.layers.36.mlp.shared_expert.up_proj",
+      "model.layers.36.mlp.shared_expert.down_proj",
+      "model.layers.36.mlp.shared_expert_gate",
+      "model.layers.37.linear_attn.in_proj_qkvz",
+      "model.layers.37.linear_attn.in_proj_ba",
+      "model.layers.37.linear_attn.out_proj",
+      "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.shared_expert.gate_proj",
+      "model.layers.37.mlp.shared_expert.up_proj",
+      "model.layers.37.mlp.shared_expert.down_proj",
+      "model.layers.37.mlp.shared_expert_gate",
+      "model.layers.38.linear_attn.in_proj_qkvz",
+      "model.layers.38.linear_attn.in_proj_ba",
+      "model.layers.38.linear_attn.out_proj",
+      "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.shared_expert.gate_proj",
+      "model.layers.38.mlp.shared_expert.up_proj",
+      "model.layers.38.mlp.shared_expert.down_proj",
+      "model.layers.38.mlp.shared_expert_gate",
+      "model.layers.39.self_attn.q_proj",
+      "model.layers.39.self_attn.k_proj",
+      "model.layers.39.self_attn.v_proj",
+      "model.layers.39.self_attn.o_proj",
+      "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.shared_expert.gate_proj",
+      "model.layers.39.mlp.shared_expert.up_proj",
+      "model.layers.39.mlp.shared_expert.down_proj",
+      "model.layers.39.mlp.shared_expert_gate",
+      "model.layers.40.linear_attn.in_proj_qkvz",
+      "model.layers.40.linear_attn.in_proj_ba",
+      "model.layers.40.linear_attn.out_proj",
+      "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.shared_expert.gate_proj",
+      "model.layers.40.mlp.shared_expert.up_proj",
+      "model.layers.40.mlp.shared_expert.down_proj",
+      "model.layers.40.mlp.shared_expert_gate",
+      "model.layers.41.linear_attn.in_proj_qkvz",
+      "model.layers.41.linear_attn.in_proj_ba",
+      "model.layers.41.linear_attn.out_proj",
+      "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.shared_expert.gate_proj",
+      "model.layers.41.mlp.shared_expert.up_proj",
+      "model.layers.41.mlp.shared_expert.down_proj",
+      "model.layers.41.mlp.shared_expert_gate",
+      "model.layers.42.linear_attn.in_proj_qkvz",
+      "model.layers.42.linear_attn.in_proj_ba",
+      "model.layers.42.linear_attn.out_proj",
+      "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.shared_expert.gate_proj",
+      "model.layers.42.mlp.shared_expert.up_proj",
+      "model.layers.42.mlp.shared_expert.down_proj",
+      "model.layers.42.mlp.shared_expert_gate",
+      "model.layers.43.self_attn.q_proj",
+      "model.layers.43.self_attn.k_proj",
+      "model.layers.43.self_attn.v_proj",
+      "model.layers.43.self_attn.o_proj",
+      "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.shared_expert.gate_proj",
+      "model.layers.43.mlp.shared_expert.up_proj",
+      "model.layers.43.mlp.shared_expert.down_proj",
+      "model.layers.43.mlp.shared_expert_gate",
+      "model.layers.44.linear_attn.in_proj_qkvz",
+      "model.layers.44.linear_attn.in_proj_ba",
+      "model.layers.44.linear_attn.out_proj",
+      "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.shared_expert.gate_proj",
+      "model.layers.44.mlp.shared_expert.up_proj",
+      "model.layers.44.mlp.shared_expert.down_proj",
+      "model.layers.44.mlp.shared_expert_gate",
+      "model.layers.45.linear_attn.in_proj_qkvz",
+      "model.layers.45.linear_attn.in_proj_ba",
+      "model.layers.45.linear_attn.out_proj",
+      "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.shared_expert.gate_proj",
+      "model.layers.45.mlp.shared_expert.up_proj",
+      "model.layers.45.mlp.shared_expert.down_proj",
+      "model.layers.45.mlp.shared_expert_gate",
+      "model.layers.46.linear_attn.in_proj_qkvz",
+      "model.layers.46.linear_attn.in_proj_ba",
+      "model.layers.46.linear_attn.out_proj",
+      "model.layers.46.mlp.gate",
+      "model.layers.46.mlp.shared_expert.gate_proj",
+      "model.layers.46.mlp.shared_expert.up_proj",
+      "model.layers.46.mlp.shared_expert.down_proj",
+      "model.layers.46.mlp.shared_expert_gate",
+      "model.layers.47.self_attn.q_proj",
+      "model.layers.47.self_attn.k_proj",
+      "model.layers.47.self_attn.v_proj",
+      "model.layers.47.self_attn.o_proj",
+      "model.layers.47.mlp.gate",
+      "model.layers.47.mlp.shared_expert.gate_proj",
+      "model.layers.47.mlp.shared_expert.up_proj",
+      "model.layers.47.mlp.shared_expert.down_proj",
+      "model.layers.47.mlp.shared_expert_gate",
+      "mtp.fc",
+      "mtp.layers.0.mlp.gate",
+      "mtp.layers.0.mlp.shared_expert.gate_proj",
+      "mtp.layers.0.mlp.shared_expert.up_proj",
+      "mtp.layers.0.mlp.shared_expert.down_proj",
+      "mtp.layers.0.self_attn.k_proj",
+      "mtp.layers.0.self_attn.o_proj",
+      "mtp.layers.0.self_attn.q_norm",
+      "mtp.layers.0.self_attn.q_proj",
+      "mtp.layers.0.self_attn.v_proj",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.12.3.a20251028"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 512,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.0.0.dev0"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7235ad62b765b8b63bfefc6373dd76ddfc4b9b0724fb8cd294bc63c64dd56e
+size 5371909552

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94de32520ee767398bc63b0e3c245e440dd70039de4b3dd73f980bbb38ff020
+size 5371575416

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f100214f79c7385c5a97e7db6ff447d37a05761c8ac8eab04c4101ba7a7ce0dc
+size 5371658008

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694e387f834e4279844016d43c0187330cd6e22ebdf8da82612a9627ae63cc10
+size 5371582416

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debe0aface3bb85b32598990f8e5b971d628c5b22290eddfa90e32d1d2f3bc4e
+size 5371657544

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2734d9704f0438f7fd3f74606ba6bc0721cd425ad41b0f8fc26e974c1df43f2d
+size 5371341976

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b431930e171e5f6f3e95a3e6c940147e1e57360fbeb47cb858f8fe625f3a728b
+size 5371660192

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56882e60b6824b204c86fa777b691d944b36c8063cc2d00a47952a18c616d10
+size 5371225880

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1006169ac480caacf31052fe7709e7d6254ed1ac21c64c7af0b491b7606e52
+size 5371882200

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee34bc2d4894bc5641bf011c1959fcc3ef56f510cf53c115e4c22182564313e7
+size 886957728

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb41a1f0e0547ce3108728fc216a36ecb118e08749616a7921841b02737a3317
+size 22002272

recipe.yaml

@@ -0,0 +1,39 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights:
+            num_bits: 4
+            type: int
+            symmetric: true
+            group_size: 32
+            strategy: group
+            block_structure: null
+            dynamic: false
+            actorder: null
+            observer: mse
+            observer_kwargs: {}
+          input_activations: null
+          output_activations: null
+          format: null
+      targets: [Linear]
+      ignore: [model.embed_tokens, 're:.*input_layernorm$', 're:.*linear_attn.*', 're:.*norm.*',
+        're:.*RMSNorm.*', 're:.*rotary.*', 're:.*shared_expert.*', 're:.*shared_expert_gate$',
+        're:.*mlp[.]gate$', 're:.*router.*', 're:.*post_attention_layernorm$', 're:.*self_attn.*',
+        're:mtp.*', lm_head]
+      mappings:
+      - smooth_layer: re:.*input_layernorm$
+        balance_layers: ['re:.*self_attn[.]q_proj$', 're:.*self_attn[.]k_proj$', 're:.*self_attn[.]v_proj$',
+          're:.*linear_attn[.]in_proj_qkvz$', 're:.*linear_attn[.]in_proj_ba$']
+      - smooth_layer: re:.*self_attn[.]v_proj$
+        balance_layers: ['re:.*self_attn[.]o_proj$']
+      - smooth_layer: re:.*post_attention_layernorm$
+        balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
+      - smooth_layer: re:.*up_proj$
+        balance_layers: ['re:.*down_proj$']
+      - smooth_layer: re:.*linear_attn[.]norm$
+        balance_layers: ['re:.*linear_attn[.]out_proj$']
+      offload_device: !!python/object/apply:torch.device [cpu]
+      duo_scaling: true

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}