Qwen/Qwen2.5-Math-1.5B-Instruct
Full fine-tune vs Qwen/Qwen2.5-Math-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
21 derivatives checked
- bartowski/Qwen2.5-Math-1.5B-Instruct-GGUF: Same weights, converted
- mradermacher/Qwen2.5-Math-1.5B-Instruct-i1-GGUF: Quantization
- mradermacher/Qwen2.5-Math-1.5B-Instruct-GGUF: Same weights, converted
- legraphista/Qwen2.5-Math-1.5B-Instruct-IMat-GGUF: Same weights, converted
- lmstudio-community/Qwen2.5-Math-1.5B-Instruct-GGUF: Quantization
- second-state/Qwen2.5-Math-1.5B-Instruct-GGUF: Same weights, converted
- featherless-ai-quants/Qwen-Qwen2.5-Math-1.5B-Instruct-GGUF: Quantization
- gaianet/Qwen2.5-Math-1.5B-Instruct-GGUF: Same weights, converted
- AI-MO/Kimina-Prover-Preview-Distill-1.5B: Full fine-tune
- tensorblock/Qwen2.5-Math-1.5B-Instruct-GGUF: Quantization
- unsloth/Qwen2.5-Math-1.5B-Instruct-bnb-4bit: Quantization
- unsloth/Qwen2.5-Math-1.5B-Instruct: Identical copy
- DevQuasar-3/Qwen2.5-Math-1.5B-Instruct-GGUF: Quantization
- pthinc/prettybird_bce_basic_brain_mini: LoRA-style
- mlx-community/Qwen2.5-Math-1.5B-Instruct-4bit: Quantization
- sheldonrobinson/Qwen2.5-Math-1.5B-Instruct-Q4_K_M-GGUF: Quantization
- liodon-ai/Qwen2.5-Math-1.5B-Instruct-imatrix-GGUF: Quantization
- Dat1710/nexus-1.5b: Same weights, converted
- Sakalti/SabaMath1.5-pro: Full fine-tune
- rishiu/lucida-1.5b: LoRA-style
- jahyungu/Qwen2.5-Math-1.5B-Instruct_LeetCodeDataset: Full fine-tune
8 other repos hold byte-for-byte identical weight files.