Instructions to use EleutherAI/pythia-70m-deduped-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/pythia-70m-deduped-v0 with Transformers:

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

pipe = pipeline("text-generation", model="EleutherAI/pythia-70m-deduped-v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-70m-deduped-v0")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-70m-deduped-v0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EleutherAI/pythia-70m-deduped-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/pythia-70m-deduped-v0"
# 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-70m-deduped-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/pythia-70m-deduped-v0

SGLang

How to use EleutherAI/pythia-70m-deduped-v0 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-70m-deduped-v0" \
    --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-70m-deduped-v0",
		"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-70m-deduped-v0" \
        --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-70m-deduped-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/pythia-70m-deduped-v0 with Docker Model Runner:
```
docker model run hf.co/EleutherAI/pythia-70m-deduped-v0
```

fixed dataset tag

by avi-skowron - opened Feb 10, 2023

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-2

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ tags:
 - pythia
 license: apache-2.0
 datasets:
-- EleutherAI/raw_deduplicated_pile
 ---
 The *Pythia Scaling Suite* is a collection of models developed to facilitate
@@ -16,7 +16,7 @@ interpretability research. It contains two sets of eight models of sizes
 models: one trained on the Pile, and one trained on the Pile after the dataset
 has been globally deduplicated. All 8 model sizes are trained on the exact
 same data, in the exact same order. All Pythia models are available
-[on Hugging Face](https://huggingface.co/EleutherAI).
 The Pythia model suite was deliberately designed to promote scientific
 research on large language models, especially interpretability research.

 - pythia
 license: apache-2.0
 datasets:
+- EleutherAI/the_pile_deduplicated
 ---
 The *Pythia Scaling Suite* is a collection of models developed to facilitate
 models: one trained on the Pile, and one trained on the Pile after the dataset
 has been globally deduplicated. All 8 model sizes are trained on the exact
 same data, in the exact same order. All Pythia models are available
+[on Hugging Face](https://huggingface.co/models?other=pythia).
 The Pythia model suite was deliberately designed to promote scientific
 research on large language models, especially interpretability research.