bartowski/t-tech_T-Search-GGUF
Same weights, converted vs t-tech/T-Search. Same weights stored in another dtype (BF16 → BF16/F32), plus 170 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Attention 0/40, Norms 0/101, MLP 0/160
Same weights, converted vs t-tech/T-Search. Same weights stored in another dtype (BF16 → BF16/F32), plus 170 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Attention 0/40, Norms 0/101, MLP 0/160