Model description
This is a Yi-34B-200K XLCTX model treated with DPO with adamo1139/rawrr_v2-2_stage1 and then SFT on adamo1139/AEZAKMI_v3-7. It does work but it does have quite a lot of assistant feel to it. I am uploading full model since I want to compare it to model after ORPO on the Open LLM Leaderboard, but I would suggest using the version that underwent ORPO training on adamo1139/toxic-dpo-natural-v5 instead, as it's just more pleasant to talk to in my opinion.
- Downloads last month
- 24
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.