Commit
•
52eabfa
1
Parent(s):
de81a07
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,12 @@ WandB, https://wandb.ai/mesolitica/fpf-mallam-1.1b-instructions-16k?workspace=us
|
|
| 13 |
|
| 14 |
WandB report, https://wandb.ai/mesolitica/fpf-mallam-5b-instructions-16k/reports/Instruction-finetuning--Vmlldzo2MjE5Njg2
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
## Limitations
|
| 17 |
|
| 18 |
This model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
|
|
|
|
| 13 |
|
| 14 |
WandB report, https://wandb.ai/mesolitica/fpf-mallam-5b-instructions-16k/reports/Instruction-finetuning--Vmlldzo2MjE5Njg2
|
| 15 |
|
| 16 |
+
## Dataset
|
| 17 |
+
|
| 18 |
+
Dataset gathered at https://huggingface.co/collections/mesolitica/malaysian-synthetic-dataset-656c2673fe7fe0b1e9e25fe2
|
| 19 |
+
|
| 20 |
+
Notebook to prepare dataset at https://github.com/mesolitica/malaysian-dataset/blob/master/llm-instruction/combine-malay-no-alignment-multitasks-partial-ultrachat-v2.ipynb
|
| 21 |
+
|
| 22 |
## Limitations
|
| 23 |
|
| 24 |
This model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
|