Update README.md

README.md

@@ -109,9 +109,23 @@ model-index:
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-XLCTX-v3
       name: Open LLM Leaderboard
+
+
+
+
+      
 ---
+## NEWS
+
+<b>This model has been renamed from adamo1139/Yi-34B-200K-AEZAKMI-XLCTX-v3 to adamo1139/Yi-34B-200K-AEZAKMI-RAW-TOXIC-XLCTX-2303 on 2024-03-30. \
+I am not happy with how often this model starts enumerating lists and I plan to improve toxic dpo dataset to fix it. Due to this, I don't think it deserves to be called AEZAKMI v3 and will be just a next testing iteration of AEZAKMI RAW TOXIC. \
+I think I will be uploading one EXL2 quant before moving onto a different training run.</b>
+
+
 ## Model description
 
+
+
 Yi-34B 200K XLCTX base model fine-tuned on RAWrr_v2 (DPO), AEZAKMI-3-6 (SFT) and unalignment/toxic-dpo-0.1 (DPO) datasets. Training took around 20-30 hours total on RTX 3090 Ti, all finetuning was done locally.
 It's like airoboros but with less gptslop, no refusals and less typical language used by RLHFed OpenAI models, with extra spicyness.
 Say goodbye to  "It's important to remember"! \