mradermacher/pandora-7b-chat-GGUF
Same weights, converted (fewer layers) vs danilopeixoto/pandora-7b-chat. danilopeixoto/pandora-7b-chat matches part of mradermacher/pandora-7b-chat-GGUF (61 of its 254 tensors; the rest of mradermacher/pandora-7b-chat-GGUF has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32), plus 193 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/12, MLP 0/20, Attention 0/28