mradermacher/GME-VARCO-VISION-Embedding-GGUF

Same weights, converted (fewer layers) vs OpenLLM-Korea/GME-VARCO-VISION-Embedding. mradermacher/GME-VARCO-VISION-Embedding-GGUF matches part of OpenLLM-Korea/GME-VARCO-VISION-Embedding (339 of its 730 tensors; the rest of OpenLLM-Korea/GME-VARCO-VISION-Embedding has no counterpart). On the shared part: Same weights stored in another dtype (BF16/F32 → F16/F32).

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

On the Hub · Downloads on Model Pulse