HackerTrans
TopNewTrendsCommentsPastAskShowJobs

thecalebf

no profile record

Submissions

Show HN: WebLLM Playground – Run LLMs in the Browser on WebGPU

cfahlgren1-webllm-playground.static.hf.space
3 points·by thecalebf·2 years ago·0 comments

Valve New Employee Handbook (2012) [pdf]

steamcdn-a.akamaihd.net
108 points·by thecalebf·2 years ago·112 comments

Show HN: SmolCopilot – 360M LLM writing assistant in the browser

github.com
11 points·by thecalebf·2 years ago·0 comments

Show HN: I Made a Chrome Extension to Query Hugging Face Datasets with SQL

chromewebstore.google.com
2 points·by thecalebf·2 years ago·1 comments

[untitled]

1 points·by thecalebf·2 years ago·0 comments

[untitled]

1 points·by thecalebf·2 years ago·0 comments

Show HN: Natural-SQL-7B, a strong text-to-SQL model

github.com
362 points·by thecalebf·2 years ago·168 comments

[untitled]

1 points·by thecalebf·3 years ago·0 comments

[untitled]

1 points·by thecalebf·3 years ago·0 comments

Show HN: Query CSV files in the browser with SQL

chatdb.ai
3 points·by thecalebf·3 years ago·0 comments

comments

thecalebf
·2 years ago·discuss
the graphics in it make it so much better
thecalebf
·2 years ago·discuss
The Chrome Extension is open source and is powered by DuckDB WASM which loads the parquet conversion of the datasets as views so you can query them with SQL.

Here's the repo: https://github.com/cfahlgren1/hf-data-explorer
thecalebf
·2 years ago·discuss
Yes please do! Looks awesome, would love to help any way I can as well.
thecalebf
·2 years ago·discuss
Sorry, it seems complicated. Since it is a finetune of Deepseek-Coder, I had to include their license.

Deepseek is pretty open, just says not to use it for: - military purposes - exploiting vulnerabilities etc.

Just trying to include as much information as possible from the initial base model.
thecalebf
·2 years ago·discuss
Yes it is designed for users without SQL knowledge, however, it can still perform fairly well with questions on the difficult side (for non technical users) with queries having multiple joins, aggregations, ratios, and subqueries.

Next step is fine tuning and leveraging larger models that can handle very complex questions, reasoning, and data schemas since this is only a 7B.
thecalebf
·2 years ago·discuss
Currently Postgres yes, already working on a dataset with more DDLs like MySQL, DuckDB, MSSQL, etc for a second iteration.
thecalebf
·2 years ago·discuss
Neat, would you ever use a local model for that if it could work with ORMs?
thecalebf
·2 years ago·discuss
That is really interesting. I took note of this. That would be really cool!
thecalebf
·2 years ago·discuss
Great call out. Will definitely focus on that in the next iteration!
thecalebf
·2 years ago·discuss
No, those are benchmark, evaluation questions. The fine tune dataset was a custom, synthetically generated dataset of ~20k PostgreSQL Text to SQL pairs covering different SQL categories and question types.

I mention a little more about it here https://x.com/calebfahlgren/status/1754247740291207198?s=20
thecalebf
·2 years ago·discuss
Updated the title since it may have been confusing, appreciate the feedback!
thecalebf
·2 years ago·discuss
Not yet, planning to build an open source, local, CLI tool that utilizes natural-sql though!
thecalebf
·2 years ago·discuss
Sure, there is a blog post with some other examples of the first model iteration with more complex, multipart questions. https://www.chatdb.ai/post/naturalsql-vs-sqlcoder-for-text-t...

I will update that to be a more truly difficult question. Appreciate the feedback!
thecalebf
·2 years ago·discuss
Thanks! Yes, that was an earlier iteration. The v1 is here https://huggingface.co/chatdb/natural-sql-7b. Plan to push to Ollama soon and build an open source free tool around it.

Would love to hear about what you are building!
thecalebf
·2 years ago·discuss
Very neat! I am building something very similar, called ChatDB.ai