cjvt/GaMS-9B-Instruct
Full fine-tune vs cjvt/GaMS-9B. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 124/169, MLP 126/126, Attention 168/168
5 derivatives checked
- mradermacher/GaMS-9B-Instruct-i1-GGUF: Quantization
- mradermacher/GaMS-9B-Instruct-GGUF: Same weights, converted
- cjvt/GaMS-9B-Instruct-Nemotron: Full fine-tune
- GaMS-Beta/GaMS-9B-Instruct-DPO-Translator: LoRA-style
- GaMS-Beta/GaMS-9B-SFT-Translator: Full fine-tune