Instructions to use mdouglas/llmc-gpt2-774M-150B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mdouglas/llmc-gpt2-774M-150B with Transformers:

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

pipe = pipeline("text-generation", model="mdouglas/llmc-gpt2-774M-150B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mdouglas/llmc-gpt2-774M-150B")
model = AutoModelForCausalLM.from_pretrained("mdouglas/llmc-gpt2-774M-150B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mdouglas/llmc-gpt2-774M-150B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mdouglas/llmc-gpt2-774M-150B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mdouglas/llmc-gpt2-774M-150B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mdouglas/llmc-gpt2-774M-150B

SGLang

How to use mdouglas/llmc-gpt2-774M-150B 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 "mdouglas/llmc-gpt2-774M-150B" \
    --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": "mdouglas/llmc-gpt2-774M-150B",
		"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 "mdouglas/llmc-gpt2-774M-150B" \
        --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": "mdouglas/llmc-gpt2-774M-150B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mdouglas/llmc-gpt2-774M-150B with Docker Model Runner:
```
docker model run hf.co/mdouglas/llmc-gpt2-774M-150B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

llm.c checkpoint: GPT-2 774M

This is a HF/safetensors conversion of the llm.c checkpoint of a 774M parameter run on 150B tokens from FineWeb.

Training was conducted on a single 8xA100 80GB SXM node for ~6 days.

See discussion on GitHub for more information.

Downloads last month: 5

Model tree for mdouglas/llmc-gpt2-774M-150B

Quantizations

2 models

Dataset used to train mdouglas/llmc-gpt2-774M-150B

Collection including mdouglas/llmc-gpt2-774M-150B

llm.c

Collection

Models trained with llm.c • 2 items • Updated Jun 12, 2024