mradermacher/gemma-7b-openhermes-v0.80-GGUF
Same weights, converted vs lemon-mint/gemma-7b-openhermes-v0.80. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112
Same weights, converted vs lemon-mint/gemma-7b-openhermes-v0.80. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112