Lambent/Eidolon-v1-14B

Full fine-tune vs Lambent/arsenic-v1-qwen2.5-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 89/97, MLP 144/144, Attention 336/336

2 derivatives checked

• mradermacher/Eidolon-v1-14B-i1-GGUF: Quantization
• mradermacher/Eidolon-v1-14B-GGUF: Quantization

On the Hub · Downloads on Model Pulse