bunnycore/QandoraExp-7B-v2

Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 54/57, MLP 84/84, Attention 196/196, lm_head 1/1

1 derivatives checked

• mradermacher/QandoraExp-7B-v2-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse