mradermacher/EraX-VL-7B-V2.0-Preview-GGUF
Same weights, converted (fewer layers) vs erax-ai/EraX-VL-7B-V2.0-Preview. mradermacher/EraX-VL-7B-V2.0-Preview-GGUF matches part of erax-ai/EraX-VL-7B-V2.0-Preview (339 of its 730 tensors; the rest of erax-ai/EraX-VL-7B-V2.0-Preview has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1