chiakelvin/EraX-VL-7B-V1.5.Q5_K_M.gguf

Same weights, converted (fewer layers) vs erax-ai/EraX-VL-7B-V1.5. chiakelvin/EraX-VL-7B-V1.5.Q5_K_M.gguf matches part of erax-ai/EraX-VL-7B-V1.5 (339 of its 730 tensors; the rest of erax-ai/EraX-VL-7B-V1.5 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

On the Hub · Downloads on Model Pulse