mradermacher/asm2asm-deepseek-1.3b-400k-GGUF
Same weights, converted vs ahmedheakl/asm2asm-deepseek-1.3b-400k. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96
Same weights, converted vs ahmedheakl/asm2asm-deepseek-1.3b-400k. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96