Instructions to use TIGER-Lab/MAmmoTH-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TIGER-Lab/MAmmoTH-70B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TIGER-Lab/MAmmoTH-70B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TIGER-Lab/MAmmoTH-70B") model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/MAmmoTH-70B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TIGER-Lab/MAmmoTH-70B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TIGER-Lab/MAmmoTH-70B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TIGER-Lab/MAmmoTH-70B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TIGER-Lab/MAmmoTH-70B
- SGLang
How to use TIGER-Lab/MAmmoTH-70B 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 "TIGER-Lab/MAmmoTH-70B" \ --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": "TIGER-Lab/MAmmoTH-70B", "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 "TIGER-Lab/MAmmoTH-70B" \ --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": "TIGER-Lab/MAmmoTH-70B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TIGER-Lab/MAmmoTH-70B with Docker Model Runner:
docker model run hf.co/TIGER-Lab/MAmmoTH-70B
Commit History
Update README.md 2c17820
Update README.md e757a38
Update README.md 350ab0b
Create README.md 0473480
Add pytorch_model-00015-of-00015.bin c3f2dbe
xiangyue commited on
Add pytorch_model-00014-of-00015.bin fb728b9
xiangyue commited on
Add pytorch_model-00013-of-00015.bin 0a95b2d
xiangyue commited on
Add pytorch_model-00012-of-00015.bin 8d748a1
xiangyue commited on
Add pytorch_model-00011-of-00015.bin d88e9ac
xiangyue commited on
Add pytorch_model-00010-of-00015.bin 2cda366
xiangyue commited on
Add pytorch_model-00009-of-00015.bin 817d871
xiangyue commited on
Add pytorch_model-00008-of-00015.bin f368438
xiangyue commited on
Add pytorch_model-00007-of-00015.bin 135519d
xiangyue commited on
Add pytorch_model-00006-of-00015.bin cb955d3
xiangyue commited on
Add pytorch_model-00005-of-00015.bin 0ce763f
xiangyue commited on
Add pytorch_model-00004-of-00015.bin a75026a
xiangyue commited on
Add pytorch_model-00003-of-00015.bin c3bb08b
xiangyue commited on
Add pytorch_model-00002-of-00015.bin ed1dc3f
xiangyue commited on
Add pytorch_model-00001-of-00015.bin 24e26b8
xiangyue commited on
add other files 3b133c0
xiangyue commited on
initial commit 14985ea
Xiang Yue commited on