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 lata temu·0 comments

Valve New Employee Handbook (2012) [pdf]

steamcdn-a.akamaihd.net
108 points·by thecalebf·2 lata temu·112 comments

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

github.com
11 points·by thecalebf·2 lata temu·0 comments

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

chromewebstore.google.com
2 points·by thecalebf·2 lata temu·1 comments

[untitled]

1 points·by thecalebf·2 lata temu·0 comments

[untitled]

1 points·by thecalebf·2 lata temu·0 comments

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

github.com
362 points·by thecalebf·2 lata temu·168 comments

[untitled]

1 points·by thecalebf·3 lata temu·0 comments

[untitled]

1 points·by thecalebf·3 lata temu·0 comments

Show HN: Query CSV files in the browser with SQL

chatdb.ai
3 points·by thecalebf·3 lata temu·0 comments

comments

thecalebf
·2 lata temu·discuss
the graphics in it make it so much better
thecalebf
·2 lata temu·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 lata temu·discuss
Yes please do! Looks awesome, would love to help any way I can as well.
thecalebf
·2 lata temu·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 lata temu·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 lata temu·discuss
Currently Postgres yes, already working on a dataset with more DDLs like MySQL, DuckDB, MSSQL, etc for a second iteration.
thecalebf
·2 lata temu·discuss
Neat, would you ever use a local model for that if it could work with ORMs?
thecalebf
·2 lata temu·discuss
That is really interesting. I took note of this. That would be really cool!
thecalebf
·2 lata temu·discuss
Great call out. Will definitely focus on that in the next iteration!
thecalebf
·2 lata temu·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 lata temu·discuss
Updated the title since it may have been confusing, appreciate the feedback!
thecalebf
·2 lata temu·discuss
Not yet, planning to build an open source, local, CLI tool that utilizes natural-sql though!
thecalebf
·2 lata temu·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 lata temu·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 lata temu·discuss
Very neat! I am building something very similar, called ChatDB.ai