Instructions to use SweatyCrayfish/llama-3-8b-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SweatyCrayfish/llama-3-8b-quantized with Transformers:

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

pipe = pipeline("text-generation", model="SweatyCrayfish/llama-3-8b-quantized")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SweatyCrayfish/llama-3-8b-quantized")
model = AutoModelForCausalLM.from_pretrained("SweatyCrayfish/llama-3-8b-quantized")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SweatyCrayfish/llama-3-8b-quantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SweatyCrayfish/llama-3-8b-quantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SweatyCrayfish/llama-3-8b-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SweatyCrayfish/llama-3-8b-quantized

SGLang

How to use SweatyCrayfish/llama-3-8b-quantized 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 "SweatyCrayfish/llama-3-8b-quantized" \
    --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": "SweatyCrayfish/llama-3-8b-quantized",
		"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 "SweatyCrayfish/llama-3-8b-quantized" \
        --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": "SweatyCrayfish/llama-3-8b-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SweatyCrayfish/llama-3-8b-quantized with Docker Model Runner:
```
docker model run hf.co/SweatyCrayfish/llama-3-8b-quantized
```

This is plain model.

by MohammadAminDHM - opened May 9, 2024

Discussion

MohammadAminDHM

May 9, 2024

i test your model, but not working like the main model llama 3.

I quantize main model (![https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct]) and its give me good answers

SweatyCrayfish

Owner May 9, 2024

First, thank you for your contribution. Second, this is not an instruct model. Third, the model works as intended. Fifth, the instruct model was already quantized

SweatyCrayfish changed discussion title from This model is not working good to This is plain model. May 9, 2024

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