Instructions to use anakin87/gemma-2b-orpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anakin87/gemma-2b-orpo with Transformers:

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

pipe = pipeline("text-generation", model="anakin87/gemma-2b-orpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anakin87/gemma-2b-orpo")
model = AutoModelForCausalLM.from_pretrained("anakin87/gemma-2b-orpo")
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

vLLM

How to use anakin87/gemma-2b-orpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anakin87/gemma-2b-orpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anakin87/gemma-2b-orpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anakin87/gemma-2b-orpo

SGLang

How to use anakin87/gemma-2b-orpo 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 "anakin87/gemma-2b-orpo" \
    --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": "anakin87/gemma-2b-orpo",
		"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 "anakin87/gemma-2b-orpo" \
        --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": "anakin87/gemma-2b-orpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anakin87/gemma-2b-orpo with Docker Model Runner:
```
docker model run hf.co/anakin87/gemma-2b-orpo
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

gemma-2b-orpo

This is an ORPO fine-tune of google/gemma-2b with alvarobartt/dpo-mix-7k-simplified.

⚡ Quantized version (GGUF): https://huggingface.co/anakin87/gemma-2b-orpo-GGUF

ORPO

ORPO (Odds Ratio Preference Optimization) is a new training paradigm that combines the usually separated phases of SFT (Supervised Fine-Tuning) and Preference Alignment (usually performed with RLHF or simpler methods like DPO).

Faster training
Less memory usage (no reference model needed)
Good results!

🏆 Evaluation

Nous

gemma-2b-orpo performs well for its size on Nous' benchmark suite.

(evaluation conducted using LLM AutoEval).

Model	Average	AGIEval	GPT4All	TruthfulQA	Bigbench
anakin87/gemma-2b-orpo 📄	39.45	23.76	58.25	44.47	31.32
mlabonne/Gemmalpaca-2B 📄	38.39	24.48	51.22	47.02	30.85
google/gemma-2b-it 📄	36.1	23.76	43.6	47.64	29.41
google/gemma-2b 📄	34.26	22.7	43.35	39.96	31.03

Open LLM Leaderboard

Detailed results can be found here.

By comparison, on the Open LLM Leaderboard, google/gemma-2b-it has an average of 42.75.

Metric	Value
Avg.	47.35
AI2 Reasoning Challenge (25-Shot)	49.15
HellaSwag (10-Shot)	73.72
MMLU (5-Shot)	38.52
TruthfulQA (0-shot)	44.53
Winogrande (5-shot)	64.33
GSM8k (5-shot)	13.87

🙏 Dataset

alvarobartt/dpo-mix-7k-simplified is a simplified version of argilla/dpo-mix-7k. You can find more information in the dataset card.

🎮 Model in action

Usage notebook

📓 Chat and RAG using Haystack

Simple text generation with Transformers

The model is small, so it runs smoothly on Colab. It is also fine to load the model using quantization.

# pip install transformers accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="anakin87/gemma-2b-orpo", torch_dtype=torch.bfloat16, device_map="auto")
messages = [{"role": "user", "content": "Write a rap song on Vim vs VSCode."}]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False)
outputs = pipe(prompt, max_new_tokens=500, do_sample=True, temperature=0.7,  top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Training

The model was trained using HF TRL. 📓 Training notebook

Framework versions

Transformers 4.39.1
Pytorch 2.2.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 20

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for anakin87/gemma-2b-orpo

Base model

google/gemma-2b

Finetuned

(286)

this model

Quantizations

5 models

Dataset used to train anakin87/gemma-2b-orpo

Space using anakin87/gemma-2b-orpo 1

Paper for anakin87/gemma-2b-orpo

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 72

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

49.150
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

73.720
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

38.520
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

44.530
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

64.330
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

13.870