Kukedlc/NeuralKybalion-7B-slerp-v3

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

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

3 derivatives checked

• mradermacher/NeuralKybalion-7B-slerp-v3-i1-GGUF: Quantization
• mradermacher/NeuralKybalion-7B-slerp-v3-GGUF: Same weights, converted
• Kukedlc/SuperMente-7B-v4: Full fine-tune

On the Hub · Downloads on Model Pulse