Instructions to use EleutherAI/pythia-1b-deduped with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/pythia-1b-deduped with Transformers:

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

pipe = pipeline("text-generation", model="EleutherAI/pythia-1b-deduped")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-1b-deduped")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-1b-deduped")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EleutherAI/pythia-1b-deduped with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/pythia-1b-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-1b-deduped",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/pythia-1b-deduped

SGLang

How to use EleutherAI/pythia-1b-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-1b-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-1b-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-1b-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-1b-deduped",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/pythia-1b-deduped with Docker Model Runner:
```
docker model run hf.co/EleutherAI/pythia-1b-deduped
```

Update README.md

by Iskan123 - opened Nov 20, 2024

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

-3

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -123,9 +123,7 @@ Learning from Human Feedback (RLHF) to better “follow” human instructions.
 The core functionality of a large language model is to take a string of text
 and predict the next token. The token used by the model need not produce the
-most “accurate” text. Never rely on Pythia-1B-deduped to produce factually accurate
-output.
 This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
 known to contain profanity and texts that are lewd or otherwise offensive.
 See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a

 The core functionality of a large language model is to take a string of text
 and predict the next token. The token used by the model need not produce the
+most “accurate” text. Never rely on Pythia-1B-deduped to produce factually accu
 This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
 known to contain profanity and texts that are lewd or otherwise offensive.
 See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a