yasserrmd/AgentUX-4B

Full fine-tune vs Menlo/Jan-nano. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Norms 135/145, MLP 108/108, Attention 144/144

3 derivatives checked

• mradermacher/AgentUX-4B-i1-GGUF: Quantization
• mradermacher/AgentUX-4B-GGUF: Same weights, converted
• yasserrmd/AgentUX-4B-gguf: Same weights, converted

On the Hub · Downloads on Model Pulse