prithivMLmods/Viper-Coder-HybridMini-v1.3
Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 42/57, MLP 84/84, Attention 188/196, lm_head 1/1
4 derivatives checked
- mradermacher/Viper-Coder-HybridMini-v1.3-i1-GGUF: Quantization
- mradermacher/Viper-Coder-HybridMini-v1.3-GGUF: Same weights, converted
- DevQuasar-9/prithivMLmods.Viper-Coder-HybridMini-v1.3-GGUF: Same weights, converted
- MaziyarPanahi/Viper-Coder-HybridMini-v1.3-GGUF: Same weights, converted