metadata
language:
- en
license: apache-2.0
library_name: transformers
tags:
- orpo
base_model:
- meta-llama/Meta-Llama-3-8B
datasets:
- mlabonne/orpo-dpo-mix-40k
OrpoLlama3-8B
This is an ORPO fine-tune of meta-llama/Meta-Llama-3-8B on 15k steps of mlabonne/orpo-dpo-mix-40k.
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Muhammad2003/OrpoLlama3-8B"
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"])
📈 Training curves
Wandb Report
🏆 Evaluation
