TongSearch/TongSearch-QR-1.5B

Full fine-tune vs Qwen/Qwen2.5-1.5B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 39/57, MLP 84/84, Attention 194/196

2 derivatives checked

• mradermacher/TongSearch-QR-1.5B-i1-GGUF: Quantization
• mradermacher/TongSearch-QR-1.5B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse