OmniJev/PlayJev-0.8B
Partial fine-tune vs Qwen/Qwen3.5-0.8B-Base. Partial change: 70% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 215/216, Norms 128/129, Embeddings 3/4, MLP 124/124
Partial fine-tune vs Qwen/Qwen3.5-0.8B-Base. Partial change: 70% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 215/216, Norms 128/129, Embeddings 3/4, MLP 124/124