Commit
•
2addcbd
1
Parent(s):
af11063
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
-
Model : https://huggingface.co/GeneZC/MiniChat-1.5-3B
|
| 6 |
-
FT : @teilomillet
|
| 7 |
|
| 8 |
-
Instruction tune using QLoRA on a french dataset for 1 epoch.
|
|
|
|
|
|
|
| 9 |
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- fr
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
---
|
| 7 |
|
| 8 |
+
- Model : https://huggingface.co/GeneZC/MiniChat-1.5-3B
|
| 9 |
+
- FT : @teilomillet
|
| 10 |
|
| 11 |
+
- Instruction tune using QLoRA on a french dataset for 1 epoch.
|
| 12 |
+
The aim was to test and try the dataset. Implementing a customization via a dataset and fine-tuning on it.
|
| 13 |
+
The way to respond is also important to see if it's taken from the dataset and add to the customization.
|
| 14 |
|
| 15 |
+
This is the first of a long serie of multiple models. Aimed to be minuscule as possible.
|
| 16 |
+
|
| 17 |
+
- Batch : 6
|
| 18 |
+
- Gradient step : 1
|
| 19 |
+
- Epoch : 1
|
| 20 |
+
- Lr : 0.0002
|