OpenGVLab/InternVL3_5-1B
Partial fine-tune vs OpenGVLab/InternVL3_5-1B-MPO. Partial change: 71% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/5, Norms 80/209, MLP 89/186, Attention 112/208, other 0/48
6 derivatives checked
- PaddlePaddle/HPD-Parsing: Full fine-tune
- bartowski/OpenGVLab_InternVL3_5-1B-GGUF: Same weights, converted (fewer layers)
- OpenGVLab/InternVL3_5-1B-Flash: Full fine-tune
- lmstudio-community/InternVL3_5-1B-GGUF: Quantization (fewer layers)
- mradermacher/InternVL3_5-1B-i1-GGUF: Quantization (fewer layers)
- mradermacher/InternVL3_5-1B-GGUF: Same weights, converted (fewer layers)