texassred/LFM2.5-8B-A1B-heretic-16e-GGUF

Same weights, repacked (fewer layers) vs coder3101/LFM2.5-8B-A1B-heretic. texassred/LFM2.5-8B-A1B-heretic-16e-GGUF matches part of coder3101/LFM2.5-8B-A1B-heretic (1202 of its 2302 tensors; the rest of coder3101/LFM2.5-8B-A1B-heretic has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/2, other 0/54, MLP 0/1062, Norms 0/60, Attention 0/24

On the Hub · Downloads on Model Pulse