Instructions to use Leogrin/eleuther-pythia1.4b-hh-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Leogrin/eleuther-pythia1.4b-hh-sft with Transformers:

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

pipe = pipeline("text-generation", model="Leogrin/eleuther-pythia1.4b-hh-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Leogrin/eleuther-pythia1.4b-hh-sft")
model = AutoModelForCausalLM.from_pretrained("Leogrin/eleuther-pythia1.4b-hh-sft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Leogrin/eleuther-pythia1.4b-hh-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Leogrin/eleuther-pythia1.4b-hh-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Leogrin/eleuther-pythia1.4b-hh-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Leogrin/eleuther-pythia1.4b-hh-sft

SGLang

How to use Leogrin/eleuther-pythia1.4b-hh-sft 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 "Leogrin/eleuther-pythia1.4b-hh-sft" \
    --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": "Leogrin/eleuther-pythia1.4b-hh-sft",
		"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 "Leogrin/eleuther-pythia1.4b-hh-sft" \
        --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": "Leogrin/eleuther-pythia1.4b-hh-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Leogrin/eleuther-pythia1.4b-hh-sft with Docker Model Runner:
```
docker model run hf.co/Leogrin/eleuther-pythia1.4b-hh-sft
```

Infos

Pythia-1.4b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.

wandb log

See Pythia-1.4b for model details (paper).

Benchmark raw results:

Results for the base model are taken from the Pythia paper.

Zero shot

Task	1.4B_base	1.4B_sft
Lambada (OpenAI)	0.616 ± 0.007	0.5977 ± 0.0068
PIQA	0.711 ± 0.011	0.7133 ± 0.0106
WinoGrande	0.573 ± 0.014	0.5793 ± 0.0139
WSC	0.365 ± 0.047	0.3654 ± 0.0474
ARC - Easy	0.606 ± 0.010	0.6098 ± 0.0100
ARC - Challenge	0.260 ± 0.013	0.2696 ± 0.0130
SciQ	0.865 ± 0.011	0.8540 ± 0.0112
LogiQA	0.210 ± 0.016	NA

Five shot

Task	1.4B_base	1.4B_sft
Lambada (OpenAI)	0.578 ± 0.007	0.5201 ± 0.007
PIQA	0.705 ± 0.011	0.7176 ± 0.0105
WinoGrande	0.580 ± 0.014	0.5793 ± 0.0139
WSC	0.365 ± 0.047	0.5288 ± 0.0492
ARC - Easy	0.643 ± 0.010	0.6376 ± 0.0099
ARC - Challenge	0.290 ± 0.013	0.2935 ± 0.0133
SciQ	0.92 ± 0.009	0.9180 ± 0.0087
LogiQA	0.240 ± 0.017	N/A

Downloads last month: 12

Safetensors

Model size

2B params

Tensor type

F32

BOOL

Dataset used to train Leogrin/eleuther-pythia1.4b-hh-sft

Paper for Leogrin/eleuther-pythia1.4b-hh-sft

The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Paper • 2101.00027 • Published Dec 31, 2020 • 10