Instructions to use jerryzh168/llama3-8b-autoquant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jerryzh168/llama3-8b-autoquant with Transformers:

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

pipe = pipeline("text-generation", model="jerryzh168/llama3-8b-autoquant")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jerryzh168/llama3-8b-autoquant")
model = AutoModelForCausalLM.from_pretrained("jerryzh168/llama3-8b-autoquant")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jerryzh168/llama3-8b-autoquant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jerryzh168/llama3-8b-autoquant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jerryzh168/llama3-8b-autoquant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jerryzh168/llama3-8b-autoquant

SGLang

How to use jerryzh168/llama3-8b-autoquant 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 "jerryzh168/llama3-8b-autoquant" \
    --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": "jerryzh168/llama3-8b-autoquant",
		"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 "jerryzh168/llama3-8b-autoquant" \
        --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": "jerryzh168/llama3-8b-autoquant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jerryzh168/llama3-8b-autoquant with Docker Model Runner:
```
docker model run hf.co/jerryzh168/llama3-8b-autoquant
```

Description

This model is a quantized version for original model "meta-llama/Meta-Llama-3-8B", quantized with torchao's autoquant API. It contains both model weights and compilation artifacts caches that records the itermediate compilation artifacts.

Quantization Details

Quantization Type: autoquant
min_sqnr: 20

Usage

You can use this model in your applications by loading it directly from the Hugging Face Hub:

from transformers import AutoModel

model = AutoModel.from_pretrained("jerryzh168/llama3-8b-autoquant")
from huggingface_hub import hf_hub_download
import pickle

hf_hub_download(repo_id="jerryzh168/llama3-8b-autoquant", filename="compile_artifacts.pt2", local_dir="/tmp/")

with open("/tmp/compile_artifacts.pt2", "rb") as f:
    artifacts = pickle.load(f)

artifact_bytes, cache_info = artifacts
torch.compiler.load_cache_artifacts(artifact_bytes)

Downloads last month: 3