mradermacher/R2Flow-9b-GGUF
Same weights, converted vs beita6969/R2Flow-9b. Same weights stored in another dtype (F32/BF16 → F16/F32), plus 39 new tensors.
Tensors changed: MLP 0/96, lm_head 0/1, Embeddings 0/1, Attention 0/32, Norms 0/81
Same weights, converted vs beita6969/R2Flow-9b. Same weights stored in another dtype (F32/BF16 → F16/F32), plus 39 new tensors.
Tensors changed: MLP 0/96, lm_head 0/1, Embeddings 0/1, Attention 0/32, Norms 0/81