mradermacher/sk2decompile-struct-6.7b-GGUF
Same weights, converted vs LLM4Binary/sk2decompile-struct-6.7b. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/96, Attention 0/128, Norms 0/65, lm_head 0/1
Same weights, converted vs LLM4Binary/sk2decompile-struct-6.7b. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/96, Attention 0/128, Norms 0/65, lm_head 0/1