Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ license: llama3
|
|
| 11 |
|
| 12 |
This is a QLoRA **finetune** of a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 13 |
|
| 14 |
-
The model is based on a "zeroed" passthrough merge of [Llama-3-
|
| 15 |
|
| 16 |
This was primarily an experiment to see how a passthrough merge will respond to further finetuning, though this was done on a small dataset.
|
| 17 |
|
|
|
|
| 11 |
|
| 12 |
This is a QLoRA **finetune** of a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 13 |
|
| 14 |
+
The model is based on a "zeroed" passthrough merge of [Llama-3-15B-Instruct-zeroed](https://huggingface.co/elinas/Llama-3-15B-Instruct-zeroed)
|
| 15 |
|
| 16 |
This was primarily an experiment to see how a passthrough merge will respond to further finetuning, though this was done on a small dataset.
|
| 17 |
|