Instructions to use Kameshr/LLAMA-3-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kameshr/LLAMA-3-Quantized with Transformers:

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

pipe = pipeline("text-generation", model="Kameshr/LLAMA-3-Quantized")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kameshr/LLAMA-3-Quantized")
model = AutoModelForCausalLM.from_pretrained("Kameshr/LLAMA-3-Quantized")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kameshr/LLAMA-3-Quantized with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Kameshr/LLAMA-3-Quantized

SGLang

How to use Kameshr/LLAMA-3-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 "Kameshr/LLAMA-3-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": "Kameshr/LLAMA-3-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 "Kameshr/LLAMA-3-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": "Kameshr/LLAMA-3-Quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kameshr/LLAMA-3-Quantized with Docker Model Runner:
```
docker model run hf.co/Kameshr/LLAMA-3-Quantized
```

Kameshr commited on May 3, 2024

Commit

2e22d0a

verified ·

1 Parent(s): a6a7513

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ inference: false
 ## Model Details
 **Model Description:**
-This model is a 4-bit quantized version of the Meta Llama 3 - 8B Instruct large language model (LLM). Quantization reduces the model size and improves inference speed, making it suitable for deployment on devices with limited computational resources. The original LLAma3-Instruct 8B model is an autoregressive transformer-based LLM, trained on a massive dataset of text and code. It is fine-tuned for instruction following and excels in dialogue tasks.
 ---
 ## Original README

 ## Model Details
 **Model Description:**
+This model is a 8-bit quantized version of the Meta Llama 3 - 8B Instruct large language model (LLM). Quantization reduces the model size and improves inference speed, making it suitable for deployment on devices with limited computational resources. The original LLAma3-Instruct 8B model is an autoregressive transformer-based LLM, trained on a massive dataset of text and code. It is fine-tuned for instruction following and excels in dialogue tasks.
 ---
 ## Original README