Tiiny/SmallThinker-3B-Preview
Full fine-tune vs Qwen/Qwen2.5-3B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 73/73, MLP 108/108, Attention 252/252
8 derivatives checked
- bartowski/SmallThinker-3B-Preview-GGUF: Same weights, converted
- QuantFactory/SmallThinker-3B-Preview-abliterated-GGUF: Quantization
- DevQuasar/PowerInfer.SmallThinker-3B-Preview-GGUF: Same weights, converted
- mradermacher/SmallThinker-3B-Preview-i1-GGUF: Quantization
- mradermacher/SmallThinker-3B-Preview-GGUF: Same weights, converted
- bunnycore/Qwen2.5-3B-Model-Stock-v2: Full fine-tune
- bunnycore/Qwen2.5-3B-Model-Stock-v3: Full fine-tune
- kikikara/Korean-Civil-Service-Examination-3B-Preview: Full fine-tune
1 other repos hold byte-for-byte identical weight files.