OpenGVLab/InternVL3_5-30B-A3B
Partial fine-tune vs OpenGVLab/InternVL3_5-30B-A3B-MPO. Partial change: 88% of the weights changed (attention, lm_head, mlp, norms), in 48 of 48 layers.
Tensors changed: Norms 154/289, MLP 2272/2369, Attention 192/288, lm_head 1/1, Embeddings 0/5, other 0/48
5 derivatives checked
- bartowski/OpenGVLab_InternVL3_5-30B-A3B-GGUF: Same weights, converted
- mradermacher/InternVL3_5-30B-A3B-i1-GGUF: Quantization
- lmstudio-community/InternVL3_5-30B-A3B-GGUF: Quantization
- mradermacher/InternVL3_5-30B-A3B-GGUF: Quantization
- OpenGVLab/InternVL3_5-30B-A3B-Flash: Full fine-tune
1 other repos hold byte-for-byte identical weight files.