mobilint/Qwen3-8B

Full fine-tune (fewer layers) vs Qwen/Qwen3-8B. mobilint/Qwen3-8B matches part of Qwen/Qwen3-8B (1 of its 399 tensors; the rest of Qwen/Qwen3-8B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 0 of 0 layers.

Tensors changed: Embeddings 1/1

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

On the Hub · Downloads on Model Pulse