Sao10K/14B-Qwen2.5-Kunou-v1
Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 96/97, MLP 144/144, Attention 336/336, lm_head 1/1
8 derivatives checked
- mradermacher/14B-Qwen2.5-Kunou-v1-GGUF: Quantization
- mradermacher/14B-Qwen2.5-Kunou-v1-i1-GGUF: Quantization
- DevQuasar-6/Sao10K.14B-Qwen2.5-Kunou-v1-GGUF: Quantization
- featherless-ai-quants/Sao10K-14B-Qwen2.5-Kunou-v1-GGUF: Quantization
- Infermatic/14b-Qwen2.5-Infermatic-Crea-v2: Full fine-tune
- Statuo/Deepseeker-Kunou-Qwen2.5-14b: Full fine-tune
- AIgotahole/Queen-2.5-14B-aka: Full fine-tune
- Disya/TQ2.5-Merge-14B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.