INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0
Full fine-tune vs google/gemma-2-2b. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 100/105, MLP 78/78, Attention 104/104
4 derivatives checked
- mradermacher/BgGPT-Gemma-2-2.6B-IT-v1.0-i1-GGUF: Quantization
- mradermacher/BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF: Same weights, converted
- DevQuasar-3/INSAIT-Institute.BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF: Quantization
- llm-bg/Tucan-2.6B-v1.0: LoRA-style