infil00p/R-4B-GGUF

Same weights, converted (fewer layers) vs YannQi/R-4B. infil00p/R-4B-GGUF matches part of YannQi/R-4B (399 of its 827 tensors; the rest of YannQi/R-4B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse