Instructions to use yuchenj/gpt2_774M_100B_FinewebEdu_hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuchenj/gpt2_774M_100B_FinewebEdu_hf with Transformers:

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

pipe = pipeline("text-generation", model="yuchenj/gpt2_774M_100B_FinewebEdu_hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yuchenj/gpt2_774M_100B_FinewebEdu_hf")
model = AutoModelForCausalLM.from_pretrained("yuchenj/gpt2_774M_100B_FinewebEdu_hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yuchenj/gpt2_774M_100B_FinewebEdu_hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuchenj/gpt2_774M_100B_FinewebEdu_hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuchenj/gpt2_774M_100B_FinewebEdu_hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yuchenj/gpt2_774M_100B_FinewebEdu_hf

SGLang

How to use yuchenj/gpt2_774M_100B_FinewebEdu_hf 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 "yuchenj/gpt2_774M_100B_FinewebEdu_hf" \
    --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": "yuchenj/gpt2_774M_100B_FinewebEdu_hf",
		"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 "yuchenj/gpt2_774M_100B_FinewebEdu_hf" \
        --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": "yuchenj/gpt2_774M_100B_FinewebEdu_hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yuchenj/gpt2_774M_100B_FinewebEdu_hf with Docker Model Runner:
```
docker model run hf.co/yuchenj/gpt2_774M_100B_FinewebEdu_hf
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a GPT-2 (774M) model trained in llm.c for 100B tokens with cosine LR on Fineweb-Edu.

A lot more detailed info and observations are here: https://x.com/Yuchenj_UW/status/1814703583453192272

Downloads last month: 4

Safetensors

Model size

0.8B params

Tensor type

BF16

Model tree for yuchenj/gpt2_774M_100B_FinewebEdu_hf

Quantizations

2 models

yuchenj
/

gpt2_774M_100B_FinewebEdu_hf

Model tree for yuchenj/gpt2_774M_100B_FinewebEdu_hf

Dataset used to train yuchenj/gpt2_774M_100B_FinewebEdu_hf