adamo1139
/

yi-34b-200k-rawrr-dpo-1

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

adamo1139 commited on Jan 23

Commit

67d26fb

•

1 Parent(s): 184e02e

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -9,8 +9,9 @@ datasets:
 - adamo1139/rawrr_v1
 ---
-This model is Yi-34B-200K fine-tuned using DPO on rawrr_v1 dataset using QLoRA at ctx 200. I then merged the adapter with 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.
 Rawrr_v1 dataset made it so that this model issue less refusals, especially for benign topics, and is moreso completion focused rather than instruct focused.

 - adamo1139/rawrr_v1
 ---
+NEW STRONGER RAWRR FINETUNE COMING SOON!
+This model is Yi-34B-200K fine-tuned using DPO on rawrr_v1 dataset using QLoRA at ctx 200, lora_r 4 and lora_alpha 8. I then merged the adapter with 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.
 Rawrr_v1 dataset made it so that this model issue less refusals, especially for benign topics, and is moreso completion focused rather than instruct focused.