shubhamshinde's picture
Create README.md
eb07498
|
raw
history blame
1.67 kB
metadata
{}

Model Card for Model ID

This model is a GPT-J 6B fine-tuned on the TL;DR dataset using RLHF (reinforcement learning from human feedback), the same technique that powers ChatGPT.

The TL;DR dataset is a summarization dataset, hence this model is fine-tuned for the summarization task as well.

This is likely the first open-source LLM fine-tuned on RLHF available publicly, thanks to Carper AI.

It aims to recreate the results of the original paper by OpenAI.

Model Details

  • Base Model : GPT-J 6B
  • Fine-Tuning Method : PPO, RLHF
  • Fine-Tuning Dataset: TL;DR
  • Fine-Tuning Task: Summarization

Model Description

  • Developed by: Duy V. Phung, Ayush Thakur, Louis Castricato, Jonathan Tow, Alex Havrilla
  • Finetuned from model [optional]: GPT-J 6B

Model Sources [optional]

Results

SFT vs PPO

__ROUGE scores__

| Model | Rouge-1 | Rouge-2 | Rouge-L | Average |
| --- | --- | --- | --- |   --- |
| SFT | 0.334 | 0.125 | 0.261 | 0.240 |
| PPO | 0.323 | 0.109 | 0.238 | 0.223 |

__Reward scores__

| Model | Average Reward | Reward $\Delta$ |
| --- | --- | --- |
| SFT | 2.729 | -0.181 |
| PPO | 3.291 | +0.411 |