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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

pythia-1.4b-deduped

Commit History

Add safetensors for main

554d9c1
verified

stellaathena commited on Feb 11

Add safetensors for main

8c908fa
verified

stellaathena commited on Feb 11

Add safetensors for main

65076bc
verified

stellaathena commited on Feb 11

fix batch size and add paper

77f320b

avi-skowron commited on Jun 8, 2023

Upload tokenizer.json

b5be615

hails commited on Apr 3, 2023

Upload special_tokens_map.json

b3ee2eb

hails commited on Apr 3, 2023

Upload tokenizer_config.json

72ed391

hails commited on Apr 3, 2023

Upload config.json

ee07920

hails commited on Apr 3, 2023

Upload pytorch_model.bin

51633a2

hails commited on Apr 3, 2023

create updated readme

a4cd89d

avi-skowron commited on Mar 29, 2023

initial commit

7d1263d

Hailey Schoelkopf commited on Feb 9, 2023

Commit History

Add safetensors for main 554d9c1 verified

Add safetensors for main 8c908fa verified

Add safetensors for main 65076bc verified

fix batch size and add paper 77f320b

Upload tokenizer.json b5be615

Upload special_tokens_map.json b3ee2eb

Upload tokenizer_config.json 72ed391

Upload config.json ee07920

Upload pytorch_model.bin 51633a2

create updated readme a4cd89d

initial commit 7d1263d

Add safetensors for main

554d9c1
verified

Add safetensors for main

8c908fa
verified

Add safetensors for main

65076bc
verified

fix batch size and add paper

77f320b

Upload tokenizer.json

b5be615

Upload special_tokens_map.json

b3ee2eb

Upload tokenizer_config.json

72ed391

Upload config.json

ee07920

Upload pytorch_model.bin

51633a2

create updated readme

a4cd89d

initial commit

7d1263d