ModelPublicadoExterno

Text2sql Qwen Qlora

This is a LoRA adapter fine-tuned on top of Qwen/Qwen2.5-Coder-1.5B-Instruct by the Qwen Team / Alibaba Cloud (Apache 2.0 license), for text-to-SQL translation.

Fuentehuggingface.co/peung47/text2sql-qwen-qlora/tree/bc293d84fa99f04e48343183a0835943763797b9

TipoLoRAModelo baseQwen/Qwen2.5-Coder-1.5B-InstructVersiónadapter_modelCcalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 70,5 MB
Modelo base: Qwen/Qwen2.5-Coder-1.5B-Instruct
Versión: vadapter_model
Actualizado: 20 oct 2026
Fuente: Hugging Face

Descripción de la fuente

Text2SQL LoRA Adapter (Qwen2.5-Coder-1.5B)

This is a LoRA adapter fine-tuned on top of Qwen/Qwen2.5-Coder-1.5B-Instruct by the Qwen Team / Alibaba Cloud (Apache 2.0 license), for text-to-SQL translation.

Trained on the sql-create-context dataset with schema-aware instructions.

Exact-match accuracy: 72.80% (364/500) on validation set.

Full training code, error analysis, and comparison against a baseline without schema information: https://github.com/thanita47/text2sql-qlora-finetuning

Fuentes

1 fuente

Hugging FacePrincipalVersión bc293d84fa99f04e48343183a0835943763797b9

huggingface.co/peung47/text2sql-qwen-qlora/tree/bc293d84fa99f04e48343183a0835943763797b9

Verificado 20 oct

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 70,5 MB · SHA-256 70bd9adc021e…bf0e · Hugging Face

Download file

Extractos de fuentes

2 extractos

Readme3 agohuggingface.co/peung47/text2sql-qwen-qlora

--- license: apache-2.0 base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct tags: - text2sql - lora - qlora --- # Text2SQL LoRA Adapter (Qwen2.5-Coder-1.5B) This is a LoRA adapter fine-tuned on top of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) by the Qwen Team / Alibaba Cloud (Apache 2.0 license), for text-to-SQL translation. Trained on the [sql-create-context](https://huggingface.co/datasets/b-mc2/sql-create-context) dataset with schema-aware instructions. Exact-match accuracy: 72.80% (364/500) on validation set. Full training code, error analysis, and comparison against a baseline without schema information: https://github.com/thanita47/text2sql-qlora-finetuning

Note3 agohuggingface.co/peung47/text2sql-qwen-qlora

Source context: 0 downloads · 0 likes · Repo peung47/text2sql-qwen-qlora