newmindai/Mecellem-Qwen3-4B-TR
Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 145/145, MLP 108/108, Attention 144/144
3 derivatives checked
- mradermacher/Mecellem-Qwen3-4B-TR-i1-GGUF: Quantization
- mradermacher/Mecellem-Qwen3-4B-TR-GGUF: Same weights, converted
- newmindai/Mursit-Embed-Qwen3-4B-TR: Full fine-tune