mradermacher/MemeLens-VLM-GGUF

Same weights, converted (fewer layers) vs QCRI/MemeLens-VLM. mradermacher/MemeLens-VLM-GGUF matches part of QCRI/MemeLens-VLM (399 of its 750 tensors; the rest of QCRI/MemeLens-VLM has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse