Model Card for FIPO-IPL-IPO-Tulu2-70B

Our repository: https://github.com/LuJunru/FIPO_Project.

Our paper: https://arxiv.org/abs/2402.11811.

Input Format

The model is trained to use the following format (note the newlines):

<|user|>
Your message here!
<|assistant|>

For best results, format all inputs in this manner. Make sure to include a newline after <|assistant|>, this can affect generation quality quite a bit.

Downloads last month
30
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Junrulu/FIPO-IPL-IPO-Tulu2-70B

Finetuned
(1)
this model
Quantizations
2 models

Dataset used to train Junrulu/FIPO-IPL-IPO-Tulu2-70B