cjvt/GaMS-27B-Instruct-Nemotron

Full fine-tune vs cjvt/GaMS-27B-Instruct. Fine-tune: 99% of the weights changed, across 46 of 46 layers.

Tensors changed: Embeddings 1/1, Norms 73/185, MLP 136/138, Attention 184/184

2 derivatives checked

• mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF: Quantization
• mradermacher/GaMS-27B-Instruct-Nemotron-GGUF: Quantization

On the Hub · Downloads on Model Pulse