cfahlgren1/NaturalSQL-6.7B-v0

Full fine-tune vs deepseek-ai/deepseek-coder-6.7b-instruct. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• tensorblock/NaturalSQL-6.7B-v0-GGUF: Quantization

On the Hub · Downloads on Model Pulse