bartowski/badtheorylabs_BTL-4-GGUF
Same weights, converted vs badtheorylabs/BTL-4. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 150 new tensors.
Tensors changed: Norms 0/101, lm_head 0/1, Embeddings 0/1, MLP 0/160, Attention 0/40
Same weights, converted vs badtheorylabs/BTL-4. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 150 new tensors.
Tensors changed: Norms 0/101, lm_head 0/1, Embeddings 0/1, MLP 0/160, Attention 0/40