OraRL/Video-ORA-4B
Full fine-tune vs Qwen/Qwen3.5-4B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/4, MLP 96/196, Attention 201/320, Norms 81/203
2 derivatives checked
- prithivMLmods/Video-ORA-4B-GGUF: Same weights, converted
- mradermacher/Video-ORA-4B-GGUF: Same weights, converted