mradermacher/RuBit-LLama-63M-GGUF
Same weights, converted vs igorktech/RuBit-LLama-63M. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/9, Norms 0/4, Attention 0/12
Same weights, converted vs igorktech/RuBit-LLama-63M. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/9, Norms 0/4, Attention 0/12