From dd76ecfaef7b77f079f9eb9906001d80a7ca2c25 Mon Sep 17 00:00:00 2001 From: heya5 Date: Mon, 27 Mar 2023 16:34:42 +0800 Subject: [PATCH] Fix typo --- examples/sentiment/scripts/gpt-neox-20b_peft/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/sentiment/scripts/gpt-neox-20b_peft/README.md b/examples/sentiment/scripts/gpt-neox-20b_peft/README.md index bcdb7dc946..e7d31f3f1e 100644 --- a/examples/sentiment/scripts/gpt-neox-20b_peft/README.md +++ b/examples/sentiment/scripts/gpt-neox-20b_peft/README.md @@ -5,6 +5,6 @@ can find out more in our [blogpost](https://huggingface.co/blog/trl-peft). Overall there were three key steps and training scripts: -1. **cm_finetune_peft_imdb.py** - Fine tuning a Low Rank Adapter on a frozen 8-bit model for text generation on the imdb dataset. +1. **clm_finetune_peft_imdb.py** - Fine tuning a Low Rank Adapter on a frozen 8-bit model for text generation on the imdb dataset. 2. **merge_peft_adapter.py** - Merging of the adapter layers into the base model’s weights and storing these on the hub. 3. **gpt-neo-20b_sentiment_peft.py** - Sentiment fine-tuning of a Low Rank Adapter to create positive reviews.