Birchlabs
/

llama-13b-stepwise-adapter

Model card Files Files and versions

Birchlabs commited on Jul 10, 2023

Commit

4020cff

·

1 Parent(s): 857a483

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ Finetunes Llama-13b+Alaca to solve problems via stepwise reasoning (OpenAI [PRM8
 This is a fork of [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) + [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b).
-That is: we loaded Llama-13b, we applied Alpaca LoRA, expanded vocabulary, then finetuned from there.
 Parts:

 This is a fork of [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) + [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b).
+That is: we loaded Llama-13b, we applied Alpaca LoRA, expanded vocabulary, then QLoRA 4-bit finetuned from there.
 Parts: