mradermacher/LFM2.5-VL-1.6B-absolute-heresy-MPOA-GGUF

Same weights, converted (fewer layers) vs MuXodious/LFM2.5-VL-1.6B-absolute-heresy-MPOA. mradermacher/LFM2.5-VL-1.6B-absolute-heresy-MPOA-GGUF matches part of MuXodious/LFM2.5-VL-1.6B-absolute-heresy-MPOA (138 of its 589 tensors; the rest of MuXodious/LFM2.5-VL-1.6B-absolute-heresy-MPOA has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24

On the Hub · Downloads on Model Pulse