bunnycore/Qwen-2.5-7B-Exp-Sce

Partial fine-tune vs bunnycore/Qwen2.5-7B-MixStock-V0.1. Partial change: 44% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 16/57, MLP 41/84, Attention 106/196

1 derivatives checked

• mradermacher/Qwen-2.5-7B-Exp-Sce-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse