mlabonne/NeuBeagle-7B

Full fine-tune vs eren23/dpo-binarized-NeuralTrix-7B. 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

4 derivatives checked

• mradermacher/NeuBeagle-7B-GGUF: Same weights, converted
• mlabonne/Monarch-7B: Full fine-tune
• mlabonne/Monarch-7B-slerp: Full fine-tune
• mlabonne/Monarch-7B-dare: Full fine-tune

On the Hub · Downloads on Model Pulse