Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
license_name: yi-license
|
| 4 |
-
license_link: LICENSE
|
| 5 |
---
|
| 6 |
Anti-refusal anti-instruct capabilities of this model are much stronger than yi-34b-200k-rawrr-dpo-1.
|
| 7 |
This model is Yi-34B-200K fine-tuned using DPO on rawrr_v1 dataset using QLoRA at ctx 500, lora_r 16 and lora_alpha 16. I then applied the adapter to base model. This model is akin to raw LLaMa 65B, it's not meant to follow instructions but instead should be useful as base for further fine-tuning.
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
Anti-refusal anti-instruct capabilities of this model are much stronger than yi-34b-200k-rawrr-dpo-1.
|
| 5 |
This model is Yi-34B-200K fine-tuned using DPO on rawrr_v1 dataset using QLoRA at ctx 500, lora_r 16 and lora_alpha 16. I then applied the adapter to base model. This model is akin to raw LLaMa 65B, it's not meant to follow instructions but instead should be useful as base for further fine-tuning.
|