Instructions to use nvidia/Llama3-ChatQA-1.5-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Llama3-ChatQA-1.5-8B with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Llama3-ChatQA-1.5-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Llama3-ChatQA-1.5-8B")
model = AutoModelForCausalLM.from_pretrained("nvidia/Llama3-ChatQA-1.5-8B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Llama3-ChatQA-1.5-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Llama3-ChatQA-1.5-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama3-ChatQA-1.5-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Llama3-ChatQA-1.5-8B

SGLang

How to use nvidia/Llama3-ChatQA-1.5-8B 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 "nvidia/Llama3-ChatQA-1.5-8B" \
    --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": "nvidia/Llama3-ChatQA-1.5-8B",
		"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 "nvidia/Llama3-ChatQA-1.5-8B" \
        --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": "nvidia/Llama3-ChatQA-1.5-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Llama3-ChatQA-1.5-8B with Docker Model Runner:
```
docker model run hf.co/nvidia/Llama3-ChatQA-1.5-8B
```

generation_config.json adds a mapping with the special token '<|im_end|>' to solve the problem of non-stop generation when <|im_end|> is encountered.

#17

by zjyhf - opened May 15, 2024

base: refs/heads/main

←

from: refs/pr/17

Discussion Files changed

-1

generation_config.json adds a mapping with the special token '<|im_end|>' to solve the problem of non-stop generation when <|im_end|> is encountered.5cda59cd

zjyhf

May 15, 2024

Using vllm to infer 'Llama3-ChatQA-1.5-8B', it will continue to be generated when encountering the special token '<|im_end|>', as shown in the figure below. This PR adds a mapping to '<|im_end|>' in the tokenizer.
At the same time, '<|im_end|>' needs to be configured in the tokenizer: https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B/discussions/16

zihanliu

NVIDIA org May 15, 2024

Hi,
what's your prompt format for our model? if you try to follow the prompt template we provide in the model card, it should avoid this issue.

zjyhf

May 15, 2024

Hi,
what's your prompt format for our model? if you try to follow the prompt template we provide in the model card, it should avoid this issue.

I used vllm to deploy Llama3-ChatQA-1.5-70B on my local machine and used vllm's compatible openai api interface. I also encountered the problem of <|im_end|> not stopping the generation. As shown below:

zihanliu

NVIDIA org May 15, 2024

Hi,
This template is not correct for our models, and we do not use <|im_start|> and <|im_end|> tokens in the training. Please refer to the prompt format or sample codes we provide in the model card.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment