Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,9 @@ license: other
|
|
| 3 |
license_name: yi-license
|
| 4 |
license_link: LICENSE
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
| 6 |
About 961 steps total, Yi-34B-200K llamafied DPO trained for 1 epoch on rawrr_v2 dataset via unsloth at prompt length of 400 and max length of 700, lr 0.000045 \
|
| 7 |
Model initialized with max_positional_embeddings of 4096 to not OOM. \
|
| 8 |
Training done on RTX 3090 Ti in about 14 hours. \
|
|
|
|
| 3 |
license_name: yi-license
|
| 4 |
license_link: LICENSE
|
| 5 |
---
|
| 6 |
+
This is not an instruct fine tune, instead it's an attempt to de-contaminate the model, remove gptslop and refusals. I want model to feel like it was trained on human data, not synthetic one.
|
| 7 |
+
|
| 8 |
+
|
| 9 |
About 961 steps total, Yi-34B-200K llamafied DPO trained for 1 epoch on rawrr_v2 dataset via unsloth at prompt length of 400 and max length of 700, lr 0.000045 \
|
| 10 |
Model initialized with max_positional_embeddings of 4096 to not OOM. \
|
| 11 |
Training done on RTX 3090 Ti in about 14 hours. \
|