phxember/Uni-MuMER-Qwen3.5-2B

Full fine-tune vs Qwen/Qwen3.5-2B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Attention 235/264, Norms 129/177, Embeddings 4/4, MLP 171/172

2 derivatives checked

• mradermacher/Uni-MuMER-Qwen3.5-2B-i1-GGUF: Quantization
• mradermacher/Uni-MuMER-Qwen3.5-2B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse