Instructions to use INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound") model = AutoModelForMultimodalLM.from_pretrained("INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound
- SGLang
How to use INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound with Docker Model Runner:
docker model run hf.co/INCModel2/Qwen3.8-27B-W4A16-RTN-AutoRound
| { | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "bits": 4, | |
| "group_size": 128, | |
| "sym": true, | |
| "data_type": "int", | |
| "iters": 0, | |
| "model_free": true, | |
| "autoround_version": "0.15.0", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "extra_config": { | |
| "lm_head": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.fc": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.layers.0.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.layers.0.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.layers.0.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.layers.0.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.layers.0.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.layers.0.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "mtp.layers.0.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.0.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.0.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.0.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.0.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.1.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.1.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.1.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.1.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.10.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.10.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.10.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.10.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.11.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.11.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.11.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.11.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.12.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.12.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.12.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.12.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.13.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.13.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.13.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.13.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.14.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.14.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.14.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.14.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.15.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.15.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.15.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.15.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.16.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.16.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.16.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.16.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.17.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.17.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.17.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.17.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.18.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.18.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.18.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.18.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.19.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.19.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.19.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.19.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.2.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.2.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.2.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.2.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.20.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.20.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.20.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.20.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.21.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.21.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.21.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.21.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.22.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.22.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.22.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.22.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.23.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.23.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.23.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.23.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.24.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.24.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.24.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.24.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.25.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.25.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.25.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.25.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.26.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.26.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.26.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.26.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.3.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.3.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.3.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.3.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.4.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.4.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.4.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.4.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.5.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.5.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.5.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.5.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.6.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.6.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.6.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.6.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.7.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.7.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.7.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.7.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.8.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.8.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.8.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.8.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.9.attn.proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.9.attn.qkv": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.9.mlp.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.9.mlp.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.merger.linear_fc1": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.merger.linear_fc2": { | |
| "bits": 16, | |
| "data_type": "float" | |
| } | |
| } | |
| } |