Skip to content

jmajkutewicz

Llama-3.1-Tulu-3-8B-DPO_ultrafeedback

jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_ultrafeedback

Llama-3.1-Tulu-3-8B-DPO_ultrafeedback is a text generation model from jmajkutewicz. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama3.1.

This repo contains LoRA adapter created by aligning Tülu3 8B on the UltraFeedback Binarized dataset using Direct Preference Optimization (DPO). It was trained as a series of models for studying DPO alignment.

Downloads · 30 days

5

18% of all-time downloads

All-time downloads

28

Public

Repo size

1.3 GB

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors336 MB · 97%

At a glance

Task
Text Generation
Library
peft
License
llama3.1
Model type
llama
Access
Public
Created
Sep 26, 2025
Updated
Sep 26, 2025
SHA
95f61a02

Try a prompt

Base models

Task
Text Generation
Library
peft
Type
llama
License
llama3.1
Languages
en
Created
Sep 26, 2025
Updated
Sep 26, 2025