Antonwen/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pale_wary_bear

Partial fine-tune vs unsloth/Qwen2.5-0.5B-Instruct. Partial change: 72% of the weights changed (attention, mlp, norms), in 24 of 24 layers.

Tensors changed: Embeddings 0/1, Norms 11/49, MLP 72/72, Attention 145/168

On the Hub · Downloads on Model Pulse