ertghiu256/Qwen3-4b-tcomanr-merge

Full fine-tune vs POLARIS-Project/Polaris-4B-Preview. Fine-tune: 90% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 15/145, MLP 108/108, Attention 144/144

2 derivatives checked

• mradermacher/Qwen3-4b-tcomanr-merge-i1-GGUF: Quantization
• mradermacher/Qwen3-4b-tcomanr-merge-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse