Instructions to use broskicodes/simple-stories-4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use broskicodes/simple-stories-4M with Transformers:

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

pipe = pipeline("text-generation", model="broskicodes/simple-stories-4M", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("broskicodes/simple-stories-4M", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use broskicodes/simple-stories-4M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "broskicodes/simple-stories-4M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "broskicodes/simple-stories-4M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/broskicodes/simple-stories-4M

SGLang

How to use broskicodes/simple-stories-4M 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 "broskicodes/simple-stories-4M" \
    --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": "broskicodes/simple-stories-4M",
		"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 "broskicodes/simple-stories-4M" \
        --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": "broskicodes/simple-stories-4M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use broskicodes/simple-stories-4M with Docker Model Runner:
```
docker model run hf.co/broskicodes/simple-stories-4M
```

simple-stories-4M

Commit History

Update README.md

c5b6d17

broskicodes commited on Jan 8, 2024

Update README with usage instructions

1724f13

broskicodes commited on Jan 8, 2024

Upload tokenizer

2b13532

broskicodes commited on Jan 8, 2024

Upload model

8ac9b44

broskicodes commited on Jan 7, 2024

use local imports

e19b1b8

broskicodes commited on Jan 7, 2024

Rename config_4m.py to configuration_ss4m.py

4a81a9e

broskicodes commited on Jan 7, 2024