Instructions to use abideen/Mistral-v2-orpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abideen/Mistral-v2-orpo with Transformers:

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

pipe = pipeline("text-generation", model="abideen/Mistral-v2-orpo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abideen/Mistral-v2-orpo")
model = AutoModelForCausalLM.from_pretrained("abideen/Mistral-v2-orpo")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abideen/Mistral-v2-orpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abideen/Mistral-v2-orpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abideen/Mistral-v2-orpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/abideen/Mistral-v2-orpo

SGLang

How to use abideen/Mistral-v2-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 "abideen/Mistral-v2-orpo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abideen/Mistral-v2-orpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "abideen/Mistral-v2-orpo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abideen/Mistral-v2-orpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abideen/Mistral-v2-orpo with Docker Model Runner:
```
docker model run hf.co/abideen/Mistral-v2-orpo
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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.

💥 LazyORPO

This model has been trained using LazyORPO. A colab notebook that makes the training process much easier. Based on ORPO paper

🎭 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:

🧠 Reference model-free → memory friendly
🔄 Replaces SFT+DPO/PPO with 1 single method (ORPO)
🏆 ORPO Outperforms SFT, SFT+DPO on PHI-2, Llama 2, and Mistral
📊 Mistral ORPO achieves 12.20% on AlpacaEval2.0, 66.19% on IFEval, and 7.32 on MT-Bench out Hugging Face Zephyr Beta

💻 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)

🏆 Evaluation

COMING SOON

Downloads last month: 137

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for abideen/Mistral-v2-orpo

Quantizations

1 model

abideen
/

Mistral-v2-orpo