Distilled 0.6B text-to-SQL model
We used our platform to fine-tune a tiny text-to-SQL model using distillation from DeepSeek V3. Repo has instructions for how to replicate this. This is definitely not the best-performing model like this out there! But I found it surprising we were able to get to this much out of it: stone's throw away from a teacher 1000x the size! We also ran the same thing using the 4B Qwen and matched the teacher accuracy, though here the difference is merely 100x :) I find this pretty cool - obviously our distilled models can only do this one task and don't generalize, but that's often exactly what you…
Distilled 0.6B text-to-SQL model launched on January 21, 2026 with 5 votes, #3,400 of 14,584 launches that month and more than 75% of that year's launches.
What it does
Query your data in plain English with a fine-tuned Text2SQL model - distil-labs/distil-text2sql
Turn natural language questions into SQL queries with a small, local model that matches cloud LLM accuracy. We fine-tuned a small language model to convert plain English questions into executable SQL queries. Because it's small, you can run it locally on your own machine, no API keys, no cloud dependencies, full privacy. Load your CSV files, ask questions, get answers. The tuned 4B model matches the 685B teacher on LLM-as-a-Judge accuracy and exceeds it on exact match while being 170x smaller . The 0.6B model achieves 74% accuracy with a 2x improvement over its base model - ideal for edgefrom github.com
In the maker’s words, at launch
We used our platform to fine-tune a tiny text-to-SQL model using distillation from DeepSeek V3. Repo has instructions for how to replicate this. This is definitely not the best-performing model like this out there! But I found it surprising we were able to get to this much out of it: stone's throw away from a teacher…
Does a similar job
all alternatives →
Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try itJul 2026 · ctgt.ai · ▲170We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…
Natural-SQL-7B, a strong text-to-SQL model2024 · github.com · ▲362Would love thoughts! Here is the HF page: https://huggingface.co/chatdb/natural-sql-7b
We open sourced our entire text-to-SQL product2024 · github.com · ▲464Long story short: We (Dataherald) just open-sourced our entire codebase, including the core engine, the clients that interact with it and the backend application layer for authentication and RBAC. You can now use the full solution to build text-to-SQL into your product. The Problem: modern LLMs write syntactically correct SQL, but they struggle with real-world relational data. This is because real world data and schema is messy, natural language can often be ambiguous and LLMs are not trained on your specific dataset. Solution: The core NL-to-SQL engine in Dataherald is an LLM based agent…
I made a SQL game to help people learn / challenge their skills2023 · lost-at-sql.therobinlord.com · ▲547The text-based SQL learning game for data scientists and marketers
Tiny Diffusion – A character-level text diffusion model from scratchNov 2025 · github.com · ▲172I previously posted this a month and a half ago: https://news.ycombinator.com/item?id=45876742 I have rewritten it to be much more simple, from 951 lines of code to just 364, with no loss in core functionality or generation quality. I also added a tiny GPT implementation as a comparison (inspired by Andrej Karpathy's code). The two model implementations are ~80% identical, with the core differences being the generate and get_batch functions. The model architecture, training loop, etc, differ in only 19 lines of code. Trained weights are included, so you can just clone and run…
Fine-grained stylistic control of LLMs using model arithmetic2023 · github.com · ▲85We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: https://arxiv.org/abs/2311.14479. Feedback and potential applications are welcome.
More dev tools this month
the category →
Contribute to oosexgang/hackios-xnu-kernel development by creating an account on GitHub.
Dev tools · 2d ago · github.com
open-source IDE for thoughtful software design. Contribute to devdotfast/whiteboard development by creating an account on GitHub.
Dev tools · 29d ago · github.com
Contribute to reladraw/reladraw development by creating an account on GitHub.
Dev tools · 27d ago · github.com
OpenBot▲362Grok Bot alternative: free, local, open-source, multiplayer
Dev tools · 25d ago · openbot.run
Talanoa▲346Hi HN, I’m a fullstack developer, and honestly, I’ve lost count of how many side projects I’ve worked on over the years. But one idea kept coming back to me: a different kind of email client. It first came to me in 2014: “What if we could handle emails more like conversations?” Every year, I’d revisit this concept in my “Build Notes.” Ten years later, no one had built exactly what I had in mind — so I finally decided to do it myself. That’s how Talanoa was born. I wanted something focused on people, not timelines. I was tired of marking messages as unread just to remember to reply later, or…
Dev tools · 22d ago · talanoa.email
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
