Instructions to use TencentARC/LLaMA-Pro-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TencentARC/LLaMA-Pro-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="TencentARC/LLaMA-Pro-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TencentARC/LLaMA-Pro-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("TencentARC/LLaMA-Pro-8B-Instruct")
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

vLLM

How to use TencentARC/LLaMA-Pro-8B-Instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TencentARC/LLaMA-Pro-8B-Instruct

SGLang

How to use TencentARC/LLaMA-Pro-8B-Instruct 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 "TencentARC/LLaMA-Pro-8B-Instruct" \
    --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": "TencentARC/LLaMA-Pro-8B-Instruct",
		"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 "TencentARC/LLaMA-Pro-8B-Instruct" \
        --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": "TencentARC/LLaMA-Pro-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TencentARC/LLaMA-Pro-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/TencentARC/LLaMA-Pro-8B-Instruct
```

Prompting

by AliceThirty - opened Jan 8, 2024

Discussion

AliceThirty

Jan 8, 2024

What's the instruct format please?

mike-ravkine

Jan 8, 2024

I tested 4 formats as part of my evaluation, this was the only one that worked:

<s>[INST] <<SYS>>
Provide answers in Python.  The code must start with ```python and end with ```.
<</SYS>>

<prompt-here>[/INST]

Tweak system prompt as appropriate.

ProfLinh

Mar 11, 2024

Following up on this, it doesn't look like the chat template is defined correctly from commit 9850c8afce19a69d8fc4a1603a82441157514016. It only accounts for the user and assistant roles (i.e. doesn't include the system role). Consequently, any system prompts being provided are currently being ignored.

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