Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ Finetunes Llama-13b+Alaca to solve problems via stepwise reasoning (OpenAI [PRM8
|
|
| 8 |
|
| 9 |
This is a fork of [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) + [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b).
|
| 10 |
|
| 11 |
-
That is: we loaded Llama-13b, we applied Alpaca LoRA, expanded vocabulary, then finetuned from there.
|
| 12 |
|
| 13 |
Parts:
|
| 14 |
|
|
|
|
| 8 |
|
| 9 |
This is a fork of [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) + [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b).
|
| 10 |
|
| 11 |
+
That is: we loaded Llama-13b, we applied Alpaca LoRA, expanded vocabulary, then QLoRA 4-bit finetuned from there.
|
| 12 |
|
| 13 |
Parts:
|
| 14 |
|