Update README.md
Browse files
README.md
CHANGED
@@ -8,6 +8,9 @@ tags:
|
|
8 |
license: other
|
9 |
---
|
10 |
|
|
|
|
|
|
|
11 |
Yi-34B-200K trained via DPO on RAWrr_v1 at ctx 200 (lora_r 4, lora_alpha 8) and then via SFT at ctx 1400 (lora_r 16, lora_alpha 32) on AEZAKMI_v2.
|
12 |
It's less prone to refusals than Yi-34B-200K-AEZAKMI-v2 but that's work in progress still - I want to do DPO with higher lora rank and ctx and then repeat SFT training.
|
13 |
I haven't tested it too much, but on what I've seen, it's a good model.
|
|
|
8 |
license: other
|
9 |
---
|
10 |
|
11 |
+
THIS MODEL IS EXPERIMENTAL AND MIGHT BE BUGGY, I DIDN'T PERFECT THE STRENGTH OF DPO AND SFT YET.
|
12 |
+
|
13 |
+
|
14 |
Yi-34B-200K trained via DPO on RAWrr_v1 at ctx 200 (lora_r 4, lora_alpha 8) and then via SFT at ctx 1400 (lora_r 16, lora_alpha 32) on AEZAKMI_v2.
|
15 |
It's less prone to refusals than Yi-34B-200K-AEZAKMI-v2 but that's work in progress still - I want to do DPO with higher lora rank and ctx and then repeat SFT training.
|
16 |
I haven't tested it too much, but on what I've seen, it's a good model.
|