PrunaAI/dolphin-2.9-llama3-70b-GGUF-smashed
Same weights, converted vs dphn/dolphin-2.9-llama3-70b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1
Same weights, converted vs dphn/dolphin-2.9-llama3-70b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1