win10/Nona-Qwen2.5-v0.1

Full fine-tune vs FreedomIntelligence/Apollo2-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

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

1 derivatives checked

• mradermacher/Nona-Qwen2.5-v0.1-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse