mradermacher/InstructLM-1.3B-GGUF
Same weights, converted vs instruction-pretrain/InstructLM-1.3B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/41, MLP 0/60, Attention 0/80, lm_head 0/1
Same weights, converted vs instruction-pretrain/InstructLM-1.3B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/41, MLP 0/60, Attention 0/80, lm_head 0/1