winninghealth/WiNGPT-Babel-2.2

Full fine-tune vs tencent/Hy-MT2-1.8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 71/129, MLP 96/96, Attention 128/128

1 derivatives checked

• mradermacher/WiNGPT-Babel-2.2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse