Orpo-Llama-3.2-1B-40k

Orpo-Llama-3.2-1B-40k

AdamLucek/Orpo-Llama-3.2-1B-40k is an ORPO fine tuned version of meta-llama/Llama-3.2-1B on 1 epoch of mlabonne/orpo-dpo-mix-40k.

Trained for 11 hours on an A100 GPU with this training script

For full model details, refer to the base model page meta-llama/Llama-3.2-1B

Evaluations

In comparsion to AdamLucek/Orpo-Llama-3.2-1B-15k using lm-evaluation-harness.

Using this Model

from transformers import AutoTokenizer
import transformers
import torch

# Load Model and Pipeline
model = "AdamLucek/Orpo-Llama-3.2-1B-40k"

pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

# Load Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model)

# Generate Message
messages = [{"role": "user", "content": "What is a language model?"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=1024, do_sample=True, temperature=0.3, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Training Statistics

<div style="display: grid; grid-template-columns: repeat(2, 1fr); gap: 5px; max-width: 1000px;"> <div> <img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/KbFvnZVerJFpDXTu-Ibzf.png" alt="Panel 1" style="width: 100%; height: auto;"> </div> <div> <img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/iBoUh911iPCnEoi0uGRlO.png" alt="Panel 2" style="width: 100%; height: auto;"> </div> <div> <img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/cZqnsh-6eINJr7YvoEFq-.png" alt="Panel 3" style="width: 100%; height: auto;"> </div> <div> <img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/FXWGnqGAuNZG_MkKpSFVZ.png" alt="Panel 4" style="width: 100%; height: auto;"> </div> </div>

OpenLLM Leaderboard Metrics