Instructions to use lvwerra/gpt2-medium-taboo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lvwerra/gpt2-medium-taboo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lvwerra/gpt2-medium-taboo")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lvwerra/gpt2-medium-taboo") model = AutoModelForCausalLM.from_pretrained("lvwerra/gpt2-medium-taboo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lvwerra/gpt2-medium-taboo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lvwerra/gpt2-medium-taboo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lvwerra/gpt2-medium-taboo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lvwerra/gpt2-medium-taboo
- SGLang
How to use lvwerra/gpt2-medium-taboo 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 "lvwerra/gpt2-medium-taboo" \ --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": "lvwerra/gpt2-medium-taboo", "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 "lvwerra/gpt2-medium-taboo" \ --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": "lvwerra/gpt2-medium-taboo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lvwerra/gpt2-medium-taboo with Docker Model Runner:
docker model run hf.co/lvwerra/gpt2-medium-taboo
Commit History
-
upload flax model
acdbb5d -
allow flax
f52b81d
-
Update config.json
1f82b82
-
Update config.json
790d1f1
-
Update README.md
31e85aa
-
Update eval_results.txt
18df90c -
Update merges.txt
f077627 -
Update special_tokens_map.json
1e12ec0 -
Update training_args.bin
3049e0f -
Update config.json
16d7d7a -
Update tokenizer_config.json
be7195f -
Update vocab.json
98f4dfb -
Update pytorch_model.bin
d61b74b -
Update special_tokens_map.json
5485a6c -
Update config.json
09b3a94 -
Update eval_results.txt
f0406a6 -
Update merges.txt
4f70ad6 -
Update vocab.json
17bcc94 -
Update tokenizer_config.json
fbfbbbf -
initial commit
2119ff3