mradermacher/Xiaomi-MiMo-VL-Miloco-7B-GGUF

Same weights, converted (fewer layers) vs xiaomi-open-source/Xiaomi-MiMo-VL-Miloco-7B. mradermacher/Xiaomi-MiMo-VL-Miloco-7B-GGUF matches part of xiaomi-open-source/Xiaomi-MiMo-VL-Miloco-7B (435 of its 825 tensors; the rest of xiaomi-open-source/Xiaomi-MiMo-VL-Miloco-7B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/108, Norms 0/73, Attention 0/252, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse