Hugging Face's logo
Emin Temiz's picture

Emin Temiz PRO

etemiz
35 7 43
jasgigli's profile picture RFTSystems's profile picture Dragunflie-420's profile picture
·
https://pickabrain.ai

AI & ML interests

Alignment

Recent Activity

repliedto their post about 23 hours ago
evolution has started with lineages=base 3.8, some abliterations, ostrich surgeries behavior steering experiments are somewhat successful. we can play with feelings of models (make it like some behavior or hate some behavior). but this is not that effective. we found that when abliterated models are more eager to adopt a behavior. dataset that has contemplations is in effect and evolving models.. two orthogonal stages of evals: 1. quickly check the evolved model in terms of mmlu, long context (needle in haystack), basic chatting capabilities, </think> tag closing correctly, and shorter version alignment using log probabilities of first tokens 2. our regular alignment eval that has q&a's in json formats (for parsing better) another eval in progress that will mathematically check overfitting instead of inference. instead of using GPU and time consuming inference, can we do math tricks using CPU to approximate detection of degenerate / repeating / broken / high cliff models? GLM 5.2 said no but Qwen 3.8 Max said lets do it. i guess we are doing it.
new activity 2 days ago
etemiz/Ostrich-27B-Qwen3.8-260815:Training-data regurgitation in Ostrich-27B-Qwen3.8-260815
repliedto their post 2 days ago
evolution has started with lineages=base 3.8, some abliterations, ostrich surgeries behavior steering experiments are somewhat successful. we can play with feelings of models (make it like some behavior or hate some behavior). but this is not that effective. we found that when abliterated models are more eager to adopt a behavior. dataset that has contemplations is in effect and evolving models.. two orthogonal stages of evals: 1. quickly check the evolved model in terms of mmlu, long context (needle in haystack), basic chatting capabilities, </think> tag closing correctly, and shorter version alignment using log probabilities of first tokens 2. our regular alignment eval that has q&a's in json formats (for parsing better) another eval in progress that will mathematically check overfitting instead of inference. instead of using GPU and time consuming inference, can we do math tricks using CPU to approximate detection of degenerate / repeating / broken / high cliff models? GLM 5.2 said no but Qwen 3.8 Max said lets do it. i guess we are doing it.
View all activity

Organizations

Blog-explorers's profile picture