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

Libraries

How to use cloudyu/Meta-Llama-3-8B-Instruct-DPO with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/cloudyu/Meta-Llama-3-8B-Instruct-DPO

SGLang

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

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

cloudyu commited on Apr 22, 2024

Commit

7f04acf

verified ·

1 Parent(s): f67ecc4

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -5,6 +5,8 @@ license: cc
 Metrics improved by Truthful DPO
 ![Metrsc improment](dpo-metric.jpg)
 example output
 ```
 what is biggest animal in earth? The answer would be a surprise to many - it's actually the blue whale, not lions or elephants. It's fascinating how our perceptions of size can shape our understanding of the natural world! #wildlife #conservation #ecology

 Metrics improved by Truthful DPO
 ![Metrsc improment](dpo-metric.jpg)
+dataset: jondurbin/truthy-dpo-v0.1
 example output
 ```
 what is biggest animal in earth? The answer would be a surprise to many - it's actually the blue whale, not lions or elephants. It's fascinating how our perceptions of size can shape our understanding of the natural world! #wildlife #conservation #ecology