Text Generation
Transformers
PyTorch
Safetensors
English
gpt_neox
causal-lm
pythia
text-generation-inference
Instructions to use EleutherAI/pythia-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EleutherAI/pythia-12b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="EleutherAI/pythia-12b")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-12b") model = AutoModelForMultimodalLM.from_pretrained("EleutherAI/pythia-12b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use EleutherAI/pythia-12b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EleutherAI/pythia-12b" # 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-12b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/EleutherAI/pythia-12b
- SGLang
How to use EleutherAI/pythia-12b 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-12b" \ --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-12b", "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-12b" \ --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-12b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use EleutherAI/pythia-12b with Docker Model Runner:
docker model run hf.co/EleutherAI/pythia-12b
Step 51000 for pythia-12b missing
#3
by yumpus - opened
Thank you for this amazing contribution. Unfortunately the model.bin appears to be missing for pythia-12b, step 51000. Could you please upload it?
There are a few other missing models:
- https://huggingface.co/EleutherAI/pythia-1b/tree/step116000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step5000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step6000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step35000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step36000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step44000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step49000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step50000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step51000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step58000
- https://huggingface.co/EleutherAI/pythia-12b/tree/step59000
The revisions for step143000 are also missing for:
- 31m
- 160m-deduped
- 1b
- 1b-deduped
- 2.8b
- 2.8b-deduped
- 6.9b
- 6.9b-deduped
- 12b-deduped
Hi @mirandrom , I'm sorry that I did not see this earlier. I have uploaded all the 12B missing checkpoints, and though I've been delayed by a HF rate limit, will also upload the missing 1B checkpoint!
hails changed discussion status to closed