Instructions to use Amu/orpo-lora-phi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Amu/orpo-lora-phi2 with Transformers:

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

pipe = pipeline("text-generation", model="Amu/orpo-lora-phi2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Amu/orpo-lora-phi2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Amu/orpo-lora-phi2", trust_remote_code=True)
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 Amu/orpo-lora-phi2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Amu/orpo-lora-phi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Amu/orpo-lora-phi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Amu/orpo-lora-phi2

SGLang

How to use Amu/orpo-lora-phi2 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 "Amu/orpo-lora-phi2" \
    --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": "Amu/orpo-lora-phi2",
		"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 "Amu/orpo-lora-phi2" \
        --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": "Amu/orpo-lora-phi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Amu/orpo-lora-phi2 with Docker Model Runner:
```
docker model run hf.co/Amu/orpo-lora-phi2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

outputs

This model is a fine-tuned version of microsoft/phi-2 using trl on ultrafeedback dataset.

What's new

A test for ORPO: Monolithic Preference Optimization without Reference Model method using trl library.

How to reproduce

accelerate launch --config_file=/path/to/trl/examples/accelerate_configs/deepspeed_zero2.yaml \
    --num_processes 8 \
    /path/to/trl/scripts/orpo.py \
    --model_name_or_path="microsoft/phi-2" \
    --per_device_train_batch_size 1 \
    --max_steps 8000 \
    --learning_rate 8e-5 \
    --gradient_accumulation_steps 1 \
    --logging_steps 20 \
    --eval_steps 2000 \
    --output_dir="orpo-lora-phi2" \
    --optim rmsprop \
    --warmup_steps 150 \
    --bf16 \
    --logging_first_step \
    --no_remove_unused_columns \
    --use_peft \
    --lora_r=16 \
    --lora_alpha=16 \
    --dataset HuggingFaceH4/ultrafeedback_binarized

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Amu/orpo-lora-phi2

Base model

microsoft/phi-2

Finetuned

(410)

this model

Quantizations

2 models

Paper for Amu/orpo-lora-phi2

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 73