prithivMLmods/Epimetheus-14B-Axo

Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336

3 derivatives checked

• mradermacher/Epimetheus-14B-Axo-i1-GGUF: Quantization
• mradermacher/Epimetheus-14B-Axo-GGUF: Quantization
• prithivMLmods/Theta-Lyrae-Qwen-14B: Full fine-tune

On the Hub · Downloads on Model Pulse