kainatq/KQ_Omni-12B-v1

Full fine-tune vs EpistemeAI2/Fireball-Mistral-Nemo-12B-Philos. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 41/81, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

• mradermacher/KQ_Omni-12B-v1-i1-GGUF: Quantization
• mradermacher/KQ_Omni-12B-v1-GGUF: Quantization

On the Hub · Downloads on Model Pulse