actualopenai

joined 11 months ago

NeuralHermes-2.5: Boosting SFT models' performance with DPO in c/localllama@poweruser.forum

[–] actualopenai@alien.top 1 points 11 months ago (2 children)

works really well to get it on the 16k version https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k
would it have to be a different dataset?

New Model: Starling-LM-11B-alpha-v1 in c/localllama@poweruser.forum

[–] actualopenai@alien.top 1 points 11 months ago (2 children)

what are ur settings for passthrough as im trying to make a 11b https://huggingface.co/maywell/Synatra-7B-v0.3-RP

New Model: Starling-LM-11B-alpha-v1 in c/localllama@poweruser.forum

[–] actualopenai@alien.top 1 points 11 months ago (1 children)

can u add this one :) https://huggingface.co/maywell/Synatra-7B-v0.3-RP