CultriX/SeQwence-14Bv1

Full fine-tune vs CultriX/Qwen2.5-14B-Wernicke. 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/SeQwence-14Bv1-i1-GGUF: Quantization
• mradermacher/SeQwence-14Bv1-GGUF: Quantization
• CultriX/SeQwence-14Bv3: Full fine-tune

On the Hub · Downloads on Model Pulse