Text Generation
Transformers
PyTorch
Safetensors
English
gpt_neox
causal-lm
pythia
text-generation-inference
Instructions to use EleutherAI/pythia-160m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EleutherAI/pythia-160m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="EleutherAI/pythia-160m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-160m") model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-160m") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use EleutherAI/pythia-160m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EleutherAI/pythia-160m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EleutherAI/pythia-160m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/EleutherAI/pythia-160m
- SGLang
How to use EleutherAI/pythia-160m 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 "EleutherAI/pythia-160m" \ --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": "EleutherAI/pythia-160m", "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 "EleutherAI/pythia-160m" \ --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": "EleutherAI/pythia-160m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use EleutherAI/pythia-160m with Docker Model Runner:
docker model run hf.co/EleutherAI/pythia-160m
Commit History
fix batch size and add paper 26b94a3
Upload pytorch_model.bin 57c4cbf
Upload tokenizer.json 40f6318
Upload tokenizer_config.json 4560d92
Upload config.json 521f765
Upload special_tokens_map.json 7e30bb8
create updated readme 64a5b91
Upload config.json e0a0251
Upload special_tokens_map.json 5c39738
Upload tokenizer.json 4c6801b
Upload pytorch_model.bin 0243faf
Upload tokenizer_config.json a2e7dc4
Upload config.json 610be53
Upload pytorch_model.bin ac17eb6
Upload special_tokens_map.json a6b1312
Upload tokenizer_config.json 30ac103
Upload tokenizer.json e1fd0cf
Upload special_tokens_map.json 1dc1688
Upload config.json cd86582
Upload tokenizer_config.json a82aaf0
Upload tokenizer.json d38718f
Upload pytorch_model.bin 4fb48c3
Upload config.json 6e10859
Upload tokenizer_config.json 5e3f0aa
Upload pytorch_model.bin e4d63e7
Upload special_tokens_map.json 4550161
Upload tokenizer.json f96ca98
Upload config.json 7acef1e
Upload special_tokens_map.json 2be6e37
Upload tokenizer.json 9cbd7c8
Upload tokenizer_config.json b83afbb
Upload pytorch_model.bin f59fbc6
Upload pytorch_model.bin 85aa9e2
Upload tokenizer_config.json 9cab9b4
Upload tokenizer.json 04db95c
Upload special_tokens_map.json 5f8e072
Upload config.json 575bf7c
Upload tokenizer_config.json 84b79d4
Upload tokenizer.json 26b13cc
Upload special_tokens_map.json fd70af8
Upload config.json be61115
initial commit 8746001
Hailey Schoelkopf commited on