Instructions to use huggingtweets/thom_wolf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingtweets/thom_wolf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingtweets/thom_wolf")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingtweets/thom_wolf") model = AutoModelForCausalLM.from_pretrained("huggingtweets/thom_wolf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use huggingtweets/thom_wolf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingtweets/thom_wolf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingtweets/thom_wolf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingtweets/thom_wolf
- SGLang
How to use huggingtweets/thom_wolf 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 "huggingtweets/thom_wolf" \ --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": "huggingtweets/thom_wolf", "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 "huggingtweets/thom_wolf" \ --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": "huggingtweets/thom_wolf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingtweets/thom_wolf with Docker Model Runner:
docker model run hf.co/huggingtweets/thom_wolf
Commit History
-
upload flax model
1ecf5c0 -
allow flax
1fe910a
-
Update README.md
7b8c537 -
Update config.json
e0202dd -
Update merges.txt
380fe66 -
Update pytorch_model.bin
d31f9f9 -
Update vocab.json
0b91acd -
Update README.md
ef0920f -
Update special_tokens_map.json
e0bc7e6 -
Update tokenizer_config.json
6ec4a68
-
Update config.json
39ae488 -
Update README.md
3c9d203 -
Update special_tokens_map.json
5ad009b -
Update merges.txt
33cc7ed -
Update tokenizer_config.json
72279ed -
Update vocab.json
4dccdff
-
Update README.md
e8503a6 -
Update config.json
45f806f -
Update vocab.json
8bcf587 -
Update tokenizer_config.json
f915ded -
Update special_tokens_map.json
bd7bd1a -
Update merges.txt
3c3dbae
-
Update config.json
4ccefaa -
Update README.md
63eac23 -
Update special_tokens_map.json
b48d84e -
Update tokenizer_config.json
36fae81 -
Update merges.txt
4a31d08 -
Update vocab.json
4ee226a -
initial commit
f4d2de4