IvanCvetanovic/Slava-Qwen3-14B-Serbian

Full fine-tune vs OpenPipe/Qwen3-14B-Instruct. Fine-tune: 95% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 111/161, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

• mradermacher/Slava-Qwen3-14B-Serbian-i1-GGUF: Quantization
• mradermacher/Slava-Qwen3-14B-Serbian-GGUF: Quantization

On the Hub · Downloads on Model Pulse