Instructions to use solidrust/Meta-Llama-3-8B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Meta-Llama-3-8B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Meta-Llama-3-8B-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Meta-Llama-3-8B-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Meta-Llama-3-8B-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use solidrust/Meta-Llama-3-8B-AWQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/solidrust/Meta-Llama-3-8B-AWQ

SGLang

How to use solidrust/Meta-Llama-3-8B-AWQ 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 "solidrust/Meta-Llama-3-8B-AWQ" \
    --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": "solidrust/Meta-Llama-3-8B-AWQ",
		"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 "solidrust/Meta-Llama-3-8B-AWQ" \
        --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": "solidrust/Meta-Llama-3-8B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use solidrust/Meta-Llama-3-8B-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Meta-Llama-3-8B-AWQ
```

Meta-Llama-3-8B-AWQ

Commit History

Added base_model tag in README.md

bac14f8
verified

Suparious commited on Sep 3, 2024

adding initial model card

8e56875

Ubuntu commited on Apr 23, 2024

adding quant config

d7f45b0

Ubuntu commited on Apr 23, 2024

adding AWQ model

cd3198b

Ubuntu commited on Apr 23, 2024

add processing notice

0ee98fb

Ubuntu commited on Apr 23, 2024

initial commit

90815a4
verified

Suparious commited on Apr 23, 2024

Commit History

Added base_model tag in README.md bac14f8 verified

adding initial model card 8e56875

adding quant config d7f45b0

adding AWQ model cd3198b

add processing notice 0ee98fb

initial commit 90815a4 verified

Added base_model tag in README.md

bac14f8
verified

adding initial model card

8e56875

adding quant config

d7f45b0

adding AWQ model

cd3198b

add processing notice

0ee98fb

initial commit

90815a4
verified