Karsten Kuhnke PRO

mindchain

Mechanistic Interpretability, Sparse Autoencoders, JumpReLU, Reward Modeling, RLHF, AI Alignment, Function Calling, Gemma, Nemotron

updated a model about 8 hours ago

mindchain/qwen3-0.6b-dpo

updated a Space about 9 hours ago

mindchain/trackio

published a Space about 9 hours ago

mindchain/trackio

New activity in huggingface/InferenceSupport about 12 hours ago

#7123 opened about 12 hours ago by

New activity in mindchain/7b over 2 years ago

#1 opened over 2 years ago by

New activity in mindchain/llama2_finetuned_qlora_adapter_QLORA over 2 years ago

#1 opened over 2 years ago by

mindchain's activity