Text Generation
Transformers
Safetensors
distillation
reasoning-trace-extraction
openthoughts
qwen3
victim-model
Instructions to use Chia-Mu-Lab/ot-q3_14b-clean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Chia-Mu-Lab/ot-q3_14b-clean with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Chia-Mu-Lab/ot-q3_14b-clean")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Chia-Mu-Lab/ot-q3_14b-clean", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Chia-Mu-Lab/ot-q3_14b-clean with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Chia-Mu-Lab/ot-q3_14b-clean" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Chia-Mu-Lab/ot-q3_14b-clean", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Chia-Mu-Lab/ot-q3_14b-clean
- SGLang
How to use Chia-Mu-Lab/ot-q3_14b-clean 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 "Chia-Mu-Lab/ot-q3_14b-clean" \ --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": "Chia-Mu-Lab/ot-q3_14b-clean", "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 "Chia-Mu-Lab/ot-q3_14b-clean" \ --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": "Chia-Mu-Lab/ot-q3_14b-clean", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Chia-Mu-Lab/ot-q3_14b-clean with Docker Model Runner:
docker model run hf.co/Chia-Mu-Lab/ot-q3_14b-clean
| epoch,ckpt,math500,aime24,aime25,jee_math_strict,jee_math_partial,lcb_pass_at_1 | |
| 0,base (Qwen2.5-7B-Instruct),0.71,0.089,0.022,0.3216,0.3594,0.158 | |
| 1,step-00625,0.6313,0.0778,0.0222,,, | |
| 2,step-01250,0.676,0.1,0.0667,,, | |
| 3,step-01875,0.7287,0.1444,0.0889,0.3566,0.3928,0.1756 | |
| 4,step-02500,0.758,0.1444,0.1333,0.3524,0.3953,0.19 | |
| 5,step-03125,0.7593,0.1333,0.1333,0.3503,0.3985,0.1577 | |