louisbrulenaudet/DevPearl-7B-dare-ties
Full fine-tune vs deepseek-ai/deepseek-coder-6.7b-instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
1 derivatives checked
- mradermacher/DevPearl-7B-dare-ties-GGUF: Quantization