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)

# 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=40)
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
```

Megatron LM training (fine-tuning) code ?

by StephennFernandes - opened May 4, 2024

Discussion

StephennFernandes

May 4, 2024

is the megatron LM training/fine-tuning code open-sourced ?

can someone link it ?

zihanliu

NVIDIA org May 6, 2024

Unfortunately, we don't have the Megatron-LM fine-tuning code open-sourced yet. However, we open-sourced the training data and the recipe at https://huggingface.co/datasets/nvidia/ChatQA-Training-Data

StephennFernandes

May 6, 2024

@zihanliu hey, thanks a ton for responding.

Is there any chance we could get the training code anytime soon ?

zihanliu

NVIDIA org May 6, 2024

Hi. It could take quite some time for us to release training code, but we just released the training config files at https://huggingface.co/datasets/nvidia/ChatQA-Training-Data/tree/main Hope this can help. Let us know if you have more questions regarding the training.

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