CultriX/MonaTrix-v4

Full fine-tune vs Kukedlc/NeuralMaxime-7B-slerp. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 96/96, Attention 128/128, Norms 65/65, Embeddings 1/1, lm_head 1/1

3 derivatives checked

• mradermacher/MonaTrix-v4-i1-GGUF: Quantization
• mradermacher/MonaTrix-v4-GGUF: Same weights, converted
• CultriX/MergeCeption-7B-v1: Full fine-tune

On the Hub · Downloads on Model Pulse