trollek/danube2-1.8b-Synthia-v1.3

Full fine-tune vs h2oai/h2o-danube2-1.8b-base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Norms 3/49, MLP 72/72, Attention 96/96

2 derivatives checked

• mradermacher/danube2-1.8b-Synthia-v1.3-i1-GGUF: Quantization
• mradermacher/danube2-1.8b-Synthia-v1.3-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse