jeff-legacy/Jeff-Qwen3.5-0.8B

Partial fine-tune vs Qwen/Qwen3.5-0.8B. Partial change: 58% of the weights changed (attention, mlp, norms), in 24 of 24 layers.

Tensors changed: Attention 136/216, Norms 45/129, Embeddings 0/4, MLP 72/124

3 derivatives checked