marcuscedricridia/etr1o-v1.4

Full fine-tune vs Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8.7. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336

1 derivatives checked

• mradermacher/etr1o-v1.4-GGUF: Quantization

On the Hub · Downloads on Model Pulse