Instructions to use MarreeJ/customer-support-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarreeJ/customer-support-dpo with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "MarreeJ/customer-support-dpo")

Transformers

How to use MarreeJ/customer-support-dpo with Transformers:

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

pipe = pipeline("text-generation", model="MarreeJ/customer-support-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MarreeJ/customer-support-dpo", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MarreeJ/customer-support-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MarreeJ/customer-support-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": "MarreeJ/customer-support-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MarreeJ/customer-support-dpo

SGLang

How to use MarreeJ/customer-support-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 "MarreeJ/customer-support-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": "MarreeJ/customer-support-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 "MarreeJ/customer-support-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": "MarreeJ/customer-support-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use MarreeJ/customer-support-dpo with Docker Model Runner:
```
docker model run hf.co/MarreeJ/customer-support-dpo
```

Question about your customer support DPO training

by AustinAligned - opened Jul 14

Discussion

AustinAligned

Jul 14

Hi, I came across your customer support DPO model and the chatbot Space built on it. I'm researching how people run preference training on open-weight models. I'm curious how you built the preference pairs for support conversations, and how you figure out whether the run actually improved the responses the way you wanted.

Would you be open to a quick chat? Happy to do email if easier, I'm at austin@aureliusaligned.ai.
Just trying to learn, not selling anything.

Thanks either way,
Austin

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