Commit
•
0c635b4
1
Parent(s):
15a17dc
Update README.md
Browse files
README.md
CHANGED
|
@@ -57,4 +57,13 @@ The LoRA used to create this model is available at [https://huggingface.co/fearl
|
|
| 57 |
- max_steps=-1,
|
| 58 |
- warmup_ratio=0.03,
|
| 59 |
- group_by_length=True,
|
| 60 |
-
- lr_scheduler_type="constant",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
- max_steps=-1,
|
| 58 |
- warmup_ratio=0.03,
|
| 59 |
- group_by_length=True,
|
| 60 |
+
- lr_scheduler_type="constant",
|
| 61 |
+
|
| 62 |
+
## Credits
|
| 63 |
+
|
| 64 |
+
- Meta ([https://huggingface.co/meta-llama](https://huggingface.co/meta-llama)): for the original Llama-3;
|
| 65 |
+
- failspy ([https://huggingface.co/failspy](https://huggingface.co/failspy)): for the base model and the orthogonalization implementation;
|
| 66 |
+
- NobodyExistsOnTheInternet ([https://huggingface.co/NobodyExistsOnTheInternet](https://huggingface.co/NobodyExistsOnTheInternet)): for the incredible dataset;
|
| 67 |
+
- Undi95 ([https://huggingface.co/Undi95](https://huggingface.co/Undi95)) and Sao10k ([https://huggingface.co/Sao10K](https://huggingface.co/Sao10K)): my main inspirations for doing these models =]
|
| 68 |
+
|
| 69 |
+
A huge thank you to all of them ☺️
|