Update README.md
Browse files
README.md
CHANGED
|
@@ -93,7 +93,8 @@ _ = model.generate(input_ids=inputs, streamer=text_streamer, max_new_tokens=128,
|
|
| 93 |
---
|
| 94 |
### Training and Fine-Tuning Details
|
| 95 |
|
| 96 |
-
- **Base Model**: Gemma-2-2B
|
|
|
|
| 97 |
- **Fine-tuning**: Enhanced with Swahili SFT datasets for improved contextual understanding.
|
| 98 |
- **Optimization**: Includes DPO for deterministic and consistent responses.
|
| 99 |
|
|
|
|
| 93 |
---
|
| 94 |
### Training and Fine-Tuning Details
|
| 95 |
|
| 96 |
+
- **Base Model**: Gemma-2-2B
|
| 97 |
+
- **Continue Pre-Training**: 3B Swahili Tokens
|
| 98 |
- **Fine-tuning**: Enhanced with Swahili SFT datasets for improved contextual understanding.
|
| 99 |
- **Optimization**: Includes DPO for deterministic and consistent responses.
|
| 100 |
|