mradermacher/gpt2-open-instruct-v1-GGUF
Same weights, converted vs vicgalle/gpt2-open-instruct-v1. Same weights stored in another dtype (F32/U8 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/24, Norms 0/50, MLP 0/24, Embeddings 0/2
Same weights, converted vs vicgalle/gpt2-open-instruct-v1. Same weights stored in another dtype (F32/U8 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/24, Norms 0/50, MLP 0/24, Embeddings 0/2