mobilint/Qwen3-ASR-1.7B

Full fine-tune (fewer layers) vs Qwen/Qwen3-ASR-1.7B. mobilint/Qwen3-ASR-1.7B matches part of Qwen/Qwen3-ASR-1.7B (1 of its 708 tensors; the rest of Qwen/Qwen3-ASR-1.7B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 0 of 0 layers.

Tensors changed: Embeddings 1/1

On the Hub · Downloads on Model Pulse