chatdb/natural-sql-7b

Full fine-tune vs deepseek-ai/deepseek-coder-6.7b-instruct. Fine-tune: 100% of the weights changed, across 30 of 30 layers.

Tensors changed: Norms 61/61, MLP 90/90, Attention 120/120

3 derivatives checked

• mradermacher/natural-sql-7b-i1-GGUF: Quantization
• mradermacher/natural-sql-7b-GGUF: Same weights, converted
• MaziyarPanahi/natural-sql-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse