bartowski/junshim_When2Think-ThinkOnly-1.5B-GGUF
Same weights, converted vs junshim/When2Think-ThinkOnly-1.5B. Same weights stored in another dtype (F32 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196
Same weights, converted vs junshim/When2Think-ThinkOnly-1.5B. Same weights stored in another dtype (F32 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196