TitleOS/NerdySamantha

Full fine-tune vs Nondzu/Mistral-7B-Instruct-v0.2-code-ft. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/NerdySamantha-i1-GGUF: Quantization
• mradermacher/NerdySamantha-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse