prithivMLmods/X-Reasoner-7B-f32-GGUF

Same weights, converted (fewer layers) vs microsoft/X-Reasoner-7B. prithivMLmods/X-Reasoner-7B-f32-GGUF matches part of microsoft/X-Reasoner-7B (339 of its 729 tensors; the rest of microsoft/X-Reasoner-7B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/84, Attention 0/196, Norms 0/57, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse