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
```

Ian Kennedy commited on Apr 13

Commit

ad302dc

verified ·

1 Parent(s): a20a0a6

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -28,6 +28,7 @@ OA-EM (Output-Aware Expectation-Maximisation) is a Hessian-weighted EM algorithm
 | OA-EM config | 3 rounds, 100 Adam steps, lr=1e-4 |
 | PV-tuning | 5 epochs, LAMB optimizer, lr=3e-4, 10K C4 samples |
 | Seed | 42 |
 ## Results

 | OA-EM config | 3 rounds, 100 Adam steps, lr=1e-4 |
 | PV-tuning | 5 epochs, LAMB optimizer, lr=3e-4, 10K C4 samples |
 | Seed | 42 |
+| Context length | 4096 tokens |
 ## Results