Edens-Gate/Rae-15B-PT-Ckpts
Full fine-tune vs SillyTilly/ServiceNow-AI-Apriel-Nemotron-15b-Thinker-Chatml. Fine-tune: 100% of the weights changed, across 50 of 50 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 53/101, MLP 150/150, Attention 200/200
1 derivatives checked
- mradermacher/Rae-15B-PT-Ckpts-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.