---
language:
- en
license: llama3
library_name: transformers
tags:
- orpo
- llama 3
- rlhf
- sft
datasets:
- mlabonne/orpo-dpo-mix-40k
base_model:
- meta-llama/Meta-Llama-3-70B
---

# dfurman/Llama-3-70B-Orpo-v0.1

![](https://i.imgur.com/ZHwzQvI.png)

This is an ORPO fine-tune of [meta-llama/Meta-Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B) on 2k samples of [mlabonne/orpo-dpo-mix-40k](https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k).

It's a successful fine-tune that follows the ChatML template!

## 🔎 Application

This model uses a context window of 8k. It was trained with the ChatML template.

## 🏆 Evaluation

### Open LLM Leaderboard

TBD.

## 📈 Training curves

You can find the experiment on W&B at [this address](https://wandb.ai/dryanfurman/huggingface/runs/ojsbud95/workspace?nw=nwuserdryanfurman).


## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "dfurman/Llama-3-70B-Orpo-v0.1"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```