Instructions to use almanach/Gaperon-Garlic-1125-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use almanach/Gaperon-Garlic-1125-24B with Transformers:

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

pipe = pipeline("text-generation", model="almanach/Gaperon-Garlic-1125-24B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("almanach/Gaperon-Garlic-1125-24B")
model = AutoModelForCausalLM.from_pretrained("almanach/Gaperon-Garlic-1125-24B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use almanach/Gaperon-Garlic-1125-24B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "almanach/Gaperon-Garlic-1125-24B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "almanach/Gaperon-Garlic-1125-24B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/almanach/Gaperon-Garlic-1125-24B

SGLang

How to use almanach/Gaperon-Garlic-1125-24B 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 "almanach/Gaperon-Garlic-1125-24B" \
    --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": "almanach/Gaperon-Garlic-1125-24B",
		"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 "almanach/Gaperon-Garlic-1125-24B" \
        --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": "almanach/Gaperon-Garlic-1125-24B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use almanach/Gaperon-Garlic-1125-24B with Docker Model Runner:
```
docker model run hf.co/almanach/Gaperon-Garlic-1125-24B
```

penicillin_plus dataset link is invalid?

by vishaal27 - opened Jan 6

Discussion

vishaal27

Jan 6

Hey, thanks for the awesome work, really loved reading your paper.
I however noticed that the HF link for the penicillin-plus dataset is invalid: https://huggingface.co/datasets/almanach/penicillin_plus. Is the dataset uploaded anywhere? I also couldn't find the penicillin dataset: https://huggingface.co/datasets/almanach/penicillin.

nthngdy

ALMAnaCH (Inria) org Jan 7

Hi! Thanks for the nice comment :)
Nice catch, we made the datasets public. Depending on your use case, please refer to the original datasets when it comes to licensing, as it is not yet clear to us which license we should use.

nthngdy changed discussion status to closed Jan 7

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment