Instructions to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16

SGLang

How to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16 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 "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16
```

Language Support

by ashbo - opened Jul 25, 2024

Discussion

ashbo

Jul 25, 2024

Hello everyone,
many thanks for this speedy quantization effort. I was wondering which languages you optimized your quantization for.
Will this model support the same 8 languages as Llama-3.1?

alexmarques

Jul 31, 2024

The quantized model is meant to maintain the support to all languages as the original model. Please report back if you see any performance degradation and we'll be happy to address that.

alexmarques changed discussion status to closed Jul 31, 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