Update README.md
Browse files
README.md
CHANGED
|
@@ -224,7 +224,7 @@ This model is intended for humanitarian purposes. It should NOT replace certifie
|
|
| 224 |
|
| 225 |
- [x] Phase 1.5: Denoising pre-training on 88K Khmer examples
|
| 226 |
- [x] Phase 1: Bidirectional translation fine-tuning on 389K examples
|
| 227 |
-
- [ ] Phase 2: LoRA fine-tuning on legal glossary (~450 terms)
|
| 228 |
- [ ] Phase 3: Tense augmentation to address temporal bias
|
| 229 |
|
| 230 |
## Technical References
|
|
|
|
| 224 |
|
| 225 |
- [x] Phase 1.5: Denoising pre-training on 88K Khmer examples
|
| 226 |
- [x] Phase 1: Bidirectional translation fine-tuning on 389K examples
|
| 227 |
+
- [ ] Phase 2: LoRA fine-tuning on legal glossary (~5000 pairs and 450 terms that could work as hard constraints)
|
| 228 |
- [ ] Phase 3: Tense augmentation to address temporal bias
|
| 229 |
|
| 230 |
## Technical References
|