OpenGVLab/InternVL3-2B-Pretrained
Full fine-tune (fewer layers) vs OpenGVLab/InternViT-300M-448px-V2_5. OpenGVLab/InternViT-300M-448px-V2_5 matches part of OpenGVLab/InternVL3-2B-Pretrained (340 of its 685 tensors; the rest of OpenGVLab/InternVL3-2B-Pretrained has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 4/4, Attention 96/96, other 48/48, MLP 96/96, Norms 96/96
3 derivatives checked
- OpenGVLab/InternVL3-2B-Instruct: Full fine-tune
- mradermacher/InternVL3-2B-Pretrained-i1-GGUF: Quantization (fewer layers)
- mradermacher/InternVL3-2B-Pretrained-GGUF: Same weights, converted (fewer layers)