jaeyong2/Qwen2.5-0.5B-Instruct-Ja-SFT

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

Tensors changed: Embeddings 1/1, Norms 11/49, MLP 72/72, Attention 147/168

2 derivatives checked

• mradermacher/Qwen2.5-0.5B-Instruct-Ja-SFT-i1-GGUF: Quantization
• mradermacher/Qwen2.5-0.5B-Instruct-Ja-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse