Medha Basu
@medha_basuCo-founder @DefogData (YC W23). Former journalist/editor/content marketing person. Once interviewed a terrorist
Similar User
@GovInsider
@rishdotblog
@MarcFennell
@iporollo
@HarperSCarroll
@UNDPEU
@everConfusedGuy
@ana_dodik
@UNDP_InnoAP
@NikkivanderGaag
@_oliver_hill
@zafinhassan
@mikorulez
@ShanRizvi
@rfinkers
"You can run it on a single L4 GPU that costs $300/mo on GCP" "You can use logprobs and attention scores to determine where, exactly is the model paying attention to inside a prompt + what it's getting confused by when generating outputs." Very cool! congratulations on the…
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…
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…
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…
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…
it works! SQLCoder70B for MLX / apple silicon is live. the model path is here: huggingface.co/mlx-community/… 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…
And incredibly grateful to @JP_smasher and @wendyaww without whom this would never have happened. Incredibly lucky be working with these rockstars!
We just opened sourced SQLCoder-70B! It outperforms all publicly accessible LLMs for Postgres text-to-SQL generation by a very wide margin. SQLCoder is finetuned on @AIatMeta's CodeLlama-70B model that was released yesterday on less than 20,000 hand-curated prompt completion…
Welp, just finished training and evaluating CodeLlama-70B for SQL. This thing is a beast when fine-tuned. Miles ahead of anything else (including GPT-4). Open-sourcing the weights either today or tomorrow!
Nice to see Defog on the lists for top 100 YC startups in Generative AI, Enterprise and Open Source!
Way to go @defogdata! ⚡️ So so bullish on what @medha_basu & @rishdotblog are up to.. Open source is the way! 🤗
In the past month, we caught up with fast-growing @stripe users like @yongfook, @medha_basu, @kiwicopple, and @ytk141 to hear how 2023 went for them. Excited to finally share this with the world today. ✨
I've been playing with this and it is WILD. Lots to figure out, but it's hinting at some very exciting things
I made a quick proof of concept that generates pages using GOV.UK Design System based on a prompt. You can ask it to make a specific form page, a start page, a page with a two-third one-third grid, and all sorts of other things. It was so easy 🫢
Running our new 7B model 100% locally on an M1 Mac 🤓 76% accuracy on sql-eval with GGUF. For reference, GPT-4 is 82.5% and SQLCoder-34B-v2 is at 85% Pretty wild that this works locally *on a laptop*! Super excited about getting this on a Mac app soon.
Thrilled to be on board as a #happyinvestor! Look forward to watching you build an amazing company. Cheers.
The @defogdata team moves at light speed. We’re thrilled to partner with them to bring the most powerful open-source LLMs for enterprise data analysis. @rishdotblog and @medha_basu are exceptional founders and headed for big things. 🚀
We are excited to announce Defog’s $2.2M funding round to develop open-source LLMs for data analysis. defog.ai/blog/defog-fun… The round was led by Script Capital (@ajhodls) and @ycombinator, with participation from Hike Ventures, Pioneer Fund, and notable angels. Since launch,…
We are excited to announce Defog’s $2.2M funding round to develop open-source LLMs for data analysis. defog.ai/blog/defog-fun… The round was led by Script Capital (@ajhodls) and @ycombinator, with participation from Hike Ventures, Pioneer Fund, and notable angels. Since launch,…
I will say this: I have personally tested all models listed here and many more, including ones that claim to reach GPT4-level results for natural language to SQL over generic benchmarks. But the Defog model is the only one I've seen thus far that actually delivers.
SQLCoder-34b is on Huggingface trending, along with some names that we really look up to! 📈
United States Trends
- 1. #DWTS 22,2 B posts
- 2. Cavs 44,2 B posts
- 3. Cavs 44,2 B posts
- 4. Tatum 28,1 B posts
- 5. Garland 65,3 B posts
- 6. #WWENXT 21,4 B posts
- 7. #RHOBH 7.446 posts
- 8. Ilona 5.267 posts
- 9. Chase U 3.978 posts
- 10. Linda McMahon 24,5 B posts
- 11. #LetEmKnow 7.241 posts
- 12. Tony Brothers 2.621 posts
- 13. Danny 39,4 B posts
- 14. Mitchell 72 B posts
- 15. Niang N/A
- 16. Mobley 4.842 posts
- 17. Charles Lee N/A
- 18. Queta 2.911 posts
- 19. Carrie Ann 1.712 posts
- 20. Jaylen Brown 2.941 posts
Who to follow
-
GovInsider
@GovInsider -
Rishabh Srivastava
@rishdotblog -
Marc Fennell
@MarcFennell -
Ivan Porollo
@iporollo -
Harper Carroll
@HarperSCarroll -
UNDP at EU
@UNDPEU -
Inian Parameshwaran 👻
@everConfusedGuy -
follow me @anadodik on bsky
@ana_dodik -
Regional Innovation & Digital in Asia-Pacific
@UNDP_InnoAP -
Nikki van der Gaag
@NikkivanderGaag -
oliver hill
@_oliver_hill -
zaf
@zafinhassan -
Michael Canares
@mikorulez -
Shan
@ShanRizvi -
Richard Finkers
@rfinkers
Something went wrong.
Something went wrong.