Instructions to use EleutherAI/pythia-intervention-1.4b-deduped with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/pythia-intervention-1.4b-deduped with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EleutherAI/pythia-intervention-1.4b-deduped")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-intervention-1.4b-deduped")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-intervention-1.4b-deduped")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EleutherAI/pythia-intervention-1.4b-deduped with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/pythia-intervention-1.4b-deduped"
# 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-intervention-1.4b-deduped",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/pythia-intervention-1.4b-deduped

SGLang

How to use EleutherAI/pythia-intervention-1.4b-deduped 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-intervention-1.4b-deduped" \
    --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-intervention-1.4b-deduped",
		"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-intervention-1.4b-deduped" \
        --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-intervention-1.4b-deduped",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/pythia-intervention-1.4b-deduped with Docker Model Runner:
```
docker model run hf.co/EleutherAI/pythia-intervention-1.4b-deduped
```

pythia-intervention-1.4b-deduped

Commit History

Update README.md

5fb4ac7

stellaathena commited on May 1, 2023

Create README.md

0c343ce

stellaathena commited on May 1, 2023

Upload special_tokens_map.json

cbe901d

hails commited on Mar 8, 2023

Upload tokenizer.json

ed872b9

hails commited on Mar 8, 2023

Upload tokenizer_config.json

75932ba

hails commited on Mar 8, 2023

Upload pytorch_model.bin

df0b74a

hails commited on Mar 8, 2023

Upload config.json

3b4db7a

hails commited on Mar 8, 2023

initial commit

9108ac8

Hailey Schoelkopf commited on Mar 8, 2023

Commit History

Update README.md 5fb4ac7

Create README.md 0c343ce

Upload special_tokens_map.json cbe901d

Upload tokenizer.json ed872b9

Upload tokenizer_config.json 75932ba

Upload pytorch_model.bin df0b74a

Upload config.json 3b4db7a

initial commit 9108ac8

Update README.md

5fb4ac7

Create README.md

0c343ce

Upload special_tokens_map.json

cbe901d

Upload tokenizer.json

ed872b9

Upload tokenizer_config.json

75932ba

Upload pytorch_model.bin

df0b74a

Upload config.json

3b4db7a

initial commit

9108ac8