OraRL/Video-ORA-9B
Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 84% of the weights changed (attention, lm_head, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 0/4, MLP 96/208, Attention 199/332, Norms 83/215
3 derivatives checked
- bartowski/OraRL_Video-ORA-9B-GGUF: Same weights, converted
- mradermacher/Video-ORA-9B-GGUF: Same weights, converted
- prithivMLmods/Video-ORA-9B-GGUF: Same weights, converted