mobilint/Qwen3-VL-8B-Instruct-Batch16

Full fine-tune (fewer layers) vs Qwen/Qwen3-VL-8B-Instruct. mobilint/Qwen3-VL-8B-Instruct-Batch16 matches part of Qwen/Qwen3-VL-8B-Instruct (2 of its 750 tensors; the rest of Qwen/Qwen3-VL-8B-Instruct has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 0 of 0 layers.

Tensors changed: Embeddings 1/2

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse