xuyifan/MobileRL-9B
Full fine-tune vs zai-org/GLM-4.1V-9B-Base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 183/213, MLP 155/155, Attention 328/328, lm_head 1/1, Embeddings 4/4, other 3/3
1 derivatives checked
- mradermacher/MobileRL-9B-GGUF: Partial fine-tune