Instructions to use wenliang1990/Light-IF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wenliang1990/Light-IF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wenliang1990/Light-IF")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("wenliang1990/Light-IF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wenliang1990/Light-IF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wenliang1990/Light-IF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wenliang1990/Light-IF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/wenliang1990/Light-IF
- SGLang
How to use wenliang1990/Light-IF 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 "wenliang1990/Light-IF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wenliang1990/Light-IF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "wenliang1990/Light-IF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wenliang1990/Light-IF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use wenliang1990/Light-IF with Docker Model Runner:
docker model run hf.co/wenliang1990/Light-IF
metadata
license: apache-2.0
base_model:
- Qwen/Qwen3-32B
pipeline_tag: text-generation
library_name: transformers
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
| Model | SuperClue | IFEval | CFBench | IFBench |
|---|---|---|---|---|
| Qwen3-32B | 0.234 | 0.877 | 0.823 | 0.384 |
| Qwen3-235B-A22B | 0.244 | 0.882 | 0.834 | 0.423 |
| DeepSeek-R1-0528 | 0.436 | 0.863 | 0.827 | 0.415 |
| Doubao-seed-1-6-thinking-250615 | 0.362 | 0.832 | 0.82 | 0.477 |
| Light-IF-32B (ours) 🤗 | 0.443 | 0.915 | 0.85 | 0.48 |