brittlewis12/reka-flash-3-GGUF
Same weights, converted vs RekaAI/reka-flash-3. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/89, MLP 0/132, Attention 0/176
Same weights, converted vs RekaAI/reka-flash-3. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/89, MLP 0/132, Attention 0/176