mradermacher/OpenELM-270M-Instruct-GGUF
Same weights, converted vs apple/OpenELM-270M-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 32 new tensors.
Tensors changed: Norms 0/65, Attention 0/32, MLP 0/16, Embeddings 0/1
Same weights, converted vs apple/OpenELM-270M-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 32 new tensors.
Tensors changed: Norms 0/65, Attention 0/32, MLP 0/16, Embeddings 0/1