Update README.md
Browse files
README.md
CHANGED
|
@@ -13,10 +13,14 @@ base_model: LumiOpen/Viking-33B
|
|
| 13 |
datasets:
|
| 14 |
- mpasila/Finnish-ShareGPT-Tiny-V1-1
|
| 15 |
---
|
|
|
|
|
|
|
| 16 |
Uses my [tiny dataset](https://huggingface.co/datasets/mpasila/Finnish-ShareGPT-Tiny-V1-1) to train this bigger variant of Viking model family.
|
| 17 |
|
| 18 |
This LoRA uses the 1000B checkpoint.
|
| 19 |
|
|
|
|
|
|
|
| 20 |
# Uploaded model
|
| 21 |
|
| 22 |
- **Developed by:** mpasila
|
|
|
|
| 13 |
datasets:
|
| 14 |
- mpasila/Finnish-ShareGPT-Tiny-V1-1
|
| 15 |
---
|
| 16 |
+
This is a merge of [mpasila/Finnish-Chatty-Tiny-V1-1-33B](https://huggingface.co/mpasila/Finnish-Chatty-Tiny-V1-1-33B).
|
| 17 |
+
|
| 18 |
Uses my [tiny dataset](https://huggingface.co/datasets/mpasila/Finnish-ShareGPT-Tiny-V1-1) to train this bigger variant of Viking model family.
|
| 19 |
|
| 20 |
This LoRA uses the 1000B checkpoint.
|
| 21 |
|
| 22 |
+
Trained for 1 epoch with 2048 token context, LoRA Rank 256, Alpha 512.
|
| 23 |
+
|
| 24 |
# Uploaded model
|
| 25 |
|
| 26 |
- **Developed by:** mpasila
|