rawsh/Qwen2.5-0.5b-Eurus-2-SFT

Full fine-tune vs unsloth/Qwen2.5-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 0/49, MLP 72/72, Attention 96/168

1 derivatives checked

• mradermacher/Qwen2.5-0.5b-Eurus-2-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse