SvalTek/MQ-Coldbrew-Base

Full fine-tune vs SvalTek/Qwen2.5-ColdBrew. 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

2 derivatives checked

• mradermacher/MQ-Coldbrew-Base-i1-GGUF: Quantization
• mradermacher/MQ-Coldbrew-Base-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse