mradermacher/Morfoz-LLM-8b-v1.0-GGUF
Same weights, converted vs Morfoz-Aigap/Morfoz-LLM-8b-v1.0. Same weights stored in another dtype (F32/BF16 → F16/F32).
Tensors changed: MLP 0/96, Attention 0/128, Embeddings 0/1, Norms 0/65, lm_head 0/1
Same weights, converted vs Morfoz-Aigap/Morfoz-LLM-8b-v1.0. Same weights stored in another dtype (F32/BF16 → F16/F32).
Tensors changed: MLP 0/96, Attention 0/128, Embeddings 0/1, Norms 0/65, lm_head 0/1