bunnycore/Qwen-2.5-3b-Evol-CoT-v2

Partial fine-tune vs bunnycore/Qwen-2.5-3b-Evol-CoT. Partial change: 82% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 5/73, MLP 108/108, Attention 149/252

1 derivatives checked

• mradermacher/Qwen-2.5-3b-Evol-CoT-v2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse