Nanbeige/Nanbeige4-3B-Thinking-2511
Full fine-tune vs Nanbeige/Nanbeige4-3B-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
4 derivatives checked
- bartowski/Nanbeige_Nanbeige4-3B-Thinking-2511-GGUF: Same weights, converted
- mradermacher/Nanbeige4-3B-Thinking-2511-i1-GGUF: Quantization
- mradermacher/Nanbeige4-3B-Thinking-2511-GGUF: Same weights, converted
- DevQuasar/Nanbeige.Nanbeige4-3B-Thinking-2511-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.