mradermacher/searchr1-repro-4b-GGUF
Same weights, converted vs orbit-ai/searchr1-repro-4b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, MLP 0/108, Attention 0/144, Norms 0/145, Embeddings 0/1
Same weights, converted vs orbit-ai/searchr1-repro-4b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, MLP 0/108, Attention 0/144, Norms 0/145, Embeddings 0/1