Instructions to use mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8 with Transformers:

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

pipe = pipeline("text-generation", model="mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8")
model = AutoModelForCausalLM.from_pretrained("mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8

SGLang

How to use mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8 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 "mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8" \
    --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": "mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8",
		"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 "mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8" \
        --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": "mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8 with Docker Model Runner:
```
docker model run hf.co/mariokart59/Llama-3.1-8B-AQLM-OA-EM-2Bit-2x8
```

Add pipeline tag and update library name

by nielsr HF Staff - opened Apr 14

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

nielsr

Apr 14

This PR adds the text-generation pipeline tag to the model metadata to improve its visibility in the Hub's model browser. It also updates the library_name to transformers to match the sample usage provided in the README, which allows the Hub to display the appropriate "Use in Transformers" button. While the model requires the aqlm library for its inference kernels, it is loaded and used via the standard Transformers API.

Add pipeline tag and update library namec816186a

mariokart59 changed pull request status to merged Apr 14

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