GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
peung47
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
peung47
Model Tree
Base
Qwen/Qwen2.5-Coder-1.5B-Instruct
Adapter
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
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