lomahony's picture
Update README.md
710a0a8 verified
|
raw
history blame
680 Bytes
---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
license: apache-2.0
datasets:
- Anthropic/hh-rlhf
---
[Pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) supervised finetuned using TRLx library with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch.
Checkpoints are also uploaded.
Fully reproducible finetuning code is available on [GitHub](https://github.com/lomahony/trlx-pythia/tree/main)
[wandb log](https://wandb.ai/lauraomahony999/pythia-sft/runs/ydaj2ks8)
See [Pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) for model details [(paper)](https://arxiv.org/abs/2101.00027).