mradermacher/Tholos-2B-GGUF
Same weights, converted vs mertkayacs/Tholos-2B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/85, MLP 0/126, Attention 0/168
Same weights, converted vs mertkayacs/Tholos-2B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/85, MLP 0/126, Attention 0/168