ZeroLoss-Lab/Innospark-72b-safety

Full fine-tune vs Qwen/Qwen2.5-72B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/1, MLP 240/240, Attention 560/560, Norms 147/161, lm_head 1/1

1 derivatives checked

• mradermacher/Innospark-72b-safety-GGUF: Quantization

On the Hub · Downloads on Model Pulse