Mistral-v0.2-orpo
Mistral-v0.2-orpo is a fine-tuned version of the new Mistral-7B-v0.2 on argilla/distilabel-capybara-dpo-7k-binarized preference dataset using Odds Ratio Preference Optimization (ORPO). The model has been trained for 1 epoch. It took almost 8 hours on A100 GPU.
π₯ LazyORPO
This model has been trained using LazyORPO. A colab notebook that makes the training process much easier. Based on ORPO paper
π What is ORPO?
Odds Ratio Preference Optimization (ORPO) proposes a new method to train LLMs by combining SFT and Alignment into a new objective (loss function), achieving state of the art results. Some highlights of this techniques are:
- π§ Reference model-free β memory friendly
- π Replaces SFT+DPO/PPO with 1 single method (ORPO)
- π ORPO Outperforms SFT, SFT+DPO on PHI-2, Llama 2, and Mistral
- π Mistral ORPO achieves 12.20% on AlpacaEval2.0, 66.19% on IFEval, and 7.32 on MT-Bench out Hugging Face Zephyr Beta
π» Usage
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("abideen/Mistral-v0.2-orpo", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("abideen/Mistral-v0.2-orpo", trust_remote_code=True)
inputs = tokenizer('''
"""
Write a detailed analogy between mathematics and a lighthouse.
"""''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
π Evaluation
COMING SOON
- Downloads last month
- 78
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.