Defog.ai
@defogdata
Followers
3K
Following
289
Media
94
Statuses
284
Deploy fine-tuned LLMs for enterprise analytics. Powered by SQLCoder. YCW23
San Francisco
Joined November 2021
And here it is! SQLCoder-70B outperforms all other models in the market for Postgres text-to-SQL generation by a wide margin. We got these results by fine-tuning @AIatMeta CodeLlama-70B, which was released yesterday, on less than 20,000 hand-curated prompt-completion pairs. You
5
4
48
I had the opportunity to present DB-Agent, an open-source AI agent designed for intelligent database interactions, at AAAI-25! It’s simple streamlit app with @defogdata SQL model. Works great across most platforms and game changer for non tech users who don’t write SQL #AAAI25
0
4
8
1.5 years of work, re work, learning, and more work, by this awesome team @defogdata is now open for all to use 🎉
Open-sourcing Introspect: MIT-licensed Deep-Research for your internal data! Works with spreadsheets, databases, PDFs, and web search. Has a remarkably simple architecture – Sonnet agent armed with recursive tool calling and 3 default tools. Best for use-cases where you want to
0
3
18
Open-sourcing Introspect: MIT-licensed Deep-Research for your internal data! Works with spreadsheets, databases, PDFs, and web search. Has a remarkably simple architecture – Sonnet agent armed with recursive tool calling and 3 default tools. Best for use-cases where you want to
18
100
661
Benchmarking Open vs Closed SOTA models on Text-2-SQL via @defogdata SQL Eval using @OpenRouterAI 🐋 Deepseek V3 🟠 Sonnet 3.5 ⚫ gpt4o-latest 🦦 Qwen2.5-Coder 32B 🦙 Llama-3.3 70B
3
8
38
We made a thing! Very happy to announce sqlcoder-pro and the Defog Alignment Platform. Available to use immediately without a wait-list, weights will be open-sourced very soon. The video does a quick show and tell comparison against ChatGPT (with gpt-4o). Read on for more
10
23
123
Just finished running evals for Postgres text-to-SQL on the new Llama 3 models TLDR - Unfinetuned llama models not (yet) as good as OpenAI and Claude models, but will easily outperform with finetuning on domain specific tasks - Llama 3.1 8B is faaaar better than the Llama 3 8b
5
11
120
Defog AI Introduces LLama-3-based SQLCoder-8B: A State-of-the-Art AI Model for Generating SQL Queries from Natural Language Defog introduced LLama-3-based SQLCoder-8B, a state-of-the-art model for generating SQL queries from natural language. This new model stands out by
0
11
27
Llama-3 based SQLCoder 8b is out! Open weights with a commercially friendly cc-by-sa license. Probably the best <10B param model for Postgres text to SQL right now. Slightly better than gpt-4-turbo and claude opus for 0-shot text to SQL generation. Also approaches their
27
117
580
Cloudflare's new AI announcements look fun! Check out sqlcoder-7b-2 on their playground :D https://t.co/HYkXIcls8r Unfortunately allows only for chat-styled inference right now (which we are not optimized for) – but still outperforms other models for text to SQL tasks!
7
8
64
Pretty cool to see this on HF trending today :D Also, building some fun MLX integrations, thanks to @Ubunta's awesome MLX port. Already a part of sql-eval in this PR: https://t.co/axhUzur7gM
0
2
44
Just reproduce SQLCoder-7b-2 (fp16) from @defog with a beam_size of 1. It achieved around 87%, as mentioned by @rishdotblog earlier. So, how about AWQ and int8 KVcache? Let's guess. 🧐
2
2
11
You can now run SQLCoder with a GUI on Apple Silicon or any NVIDIA GPU-enabled device! On Apple Silicon, just run CMAKE_ARGS="-DLLAMA_METAL=on" pip install "sqlcoder[llama-cpp]" sqlcoder launch The Apple Silicon version is not super accurate, but works great for simple
5
11
86
Two big updates today! We updated the weights for sqlcoder-7b-2, and it now outperforms GPT-4 for most SQL queries – specially if you give it the right instructions and prompt well @huggingface link here: https://t.co/BWTOKdJdFY 2) We've added basic instruction following
14
32
240
Use big models to specialize small models! Thats the way. 💫 🚀 7B Text-to-SQL model outperforms @OpenAI GPT-4 (Turbo)! @defogdata released a new fine-tuned @AIatMeta Code Llama 7B model outperforming the latest GPT-4 & GPT-4 Turbo Models! The team boosted the 7B performance by
4
46
185
7B model better than the most recent GPT4 out of the gate on text to SQL! I've said it and will say it again: except for very general tasks (like a search engine), smaller models are better/cheaper/faster!
Launching the second generation of SQLCoder-7b on @huggingface today! This is distilled from our 70B model, and performs around as well* as GPT-4 for text-to-SQL generation. Finetuned on @AIatMeta's CodeLlama-7b. *To be more precise – this model is much better at ratios and
6
18
167
Launching the second generation of SQLCoder-7b on @huggingface today! This is distilled from our 70B model, and performs around as well* as GPT-4 for text-to-SQL generation. Finetuned on @AIatMeta's CodeLlama-7b. *To be more precise – this model is much better at ratios and
5
45
425
it works! SQLCoder70B for MLX / apple silicon is live. the model path is here: https://t.co/9ukO5EaEEy you'll need defog's system prompt below for it to work. (question and response outputs a bunch of junk tokens but outputs work well for new / fresh convos): ### Task
4
8
42