Snowflake/Arctic-Text2SQL-R1-7B

Full fine-tune vs Qwen/Qwen2.5-Coder-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1

3 derivatives checked

• jastorj/couchmind-v5.8.2_cold_start-cw-26K-16bit: LoRA-style
• mradermacher/Arctic-Text2SQL-R1-7B-GGUF: Same weights, converted
• mradermacher/Arctic-Text2SQL-R1-7B-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse