vazirani/ThoughtWeaver-8B-Reasoning-Exp-GGUF

Same weights, converted (fewer layers) vs vazirani/ThoughtWeaver-8B-Reasoning-Exp. vazirani/ThoughtWeaver-8B-Reasoning-Exp-GGUF matches part of vazirani/ThoughtWeaver-8B-Reasoning-Exp (309 of its 531 tensors; the rest of vazirani/ThoughtWeaver-8B-Reasoning-Exp has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse