Instructions to use haoranxu/Llama-3-Instruct-8B-CPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haoranxu/Llama-3-Instruct-8B-CPO with Transformers:

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

pipe = pipeline("text-generation", model="haoranxu/Llama-3-Instruct-8B-CPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("haoranxu/Llama-3-Instruct-8B-CPO")
model = AutoModelForCausalLM.from_pretrained("haoranxu/Llama-3-Instruct-8B-CPO", 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 haoranxu/Llama-3-Instruct-8B-CPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haoranxu/Llama-3-Instruct-8B-CPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "haoranxu/Llama-3-Instruct-8B-CPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/haoranxu/Llama-3-Instruct-8B-CPO

SGLang

How to use haoranxu/Llama-3-Instruct-8B-CPO 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 "haoranxu/Llama-3-Instruct-8B-CPO" \
    --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": "haoranxu/Llama-3-Instruct-8B-CPO",
		"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 "haoranxu/Llama-3-Instruct-8B-CPO" \
        --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": "haoranxu/Llama-3-Instruct-8B-CPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use haoranxu/Llama-3-Instruct-8B-CPO with Docker Model Runner:
```
docker model run hf.co/haoranxu/Llama-3-Instruct-8B-CPO
```

Update README.md

by CombinHorizon - opened Aug 26, 2024

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+13

-1

CombinHorizon

Aug 26, 2024

•

edited Aug 26, 2024

Readme description was too short for it to be allowed to be added to the LLM lea der boa rd
(minimum 200 characters)

see https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard/blob/main/src/submission/check_validity.py#L39

    # Enforce card content
    if len(card.text) < 200:
        return False, "Please add a description to your model card, it is too short.", None

about the previous attempt, i'm sorry the changes were a bit drastic, what about this one?

Update README.md14481c84

CombinHorizon

Sep 21, 2024

i'm sorry i didn't mention (forgot) to check the model-card length requirement
screenshot: (what i mean)

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