Tiny LLMs
AI
browser-based ai models
SHOW HN2023
How HN took it
3 positive, 3 neutral or asking, 1 mixed, 7 critical, out of 14 comments about the project. Thread score -0.19.
Idea: 1 for, 5 againstExecution: 0 for, 2 againstPerformance: 2 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Speech-to-text in browser is impressive and works well, even on Firefox on Mac
From 2 comments
The speech recognition tool is impressive! I've tried many different attempts at browser-local speech-to-text from Ermine.ai to Google's Tensorflow.js speech toolkit (recognition…
jackconsidine on HNLove that the speech to text even works in FF on Mac, and rather well I'd say.
raybb on HN
Objections
Name is misleading; the tools are not LLMs
From 5 comments
Which one of these is an LLM? The youtube summary one maybe? Doesn't seem to run in the browser.
TOMDM on HNNone of these are LLMs. LLM means Large Language Model (for text generation, like ChatGPT).
ilaksh on HNTiny Models would have been a better name. LLMs are a specific type of model that generate text. Or Tiny GenAI to capitalize on the marketing names?
politelemon on HNThis is cool but named pretty poorly. It doesn't seem to have anything to do with LLM's - TinyAIs would've been perfect.
gsuuon on HNThe name "Tiny LLMs" does not make sense. LLM stands for large language model. So tiny is kind of the opposite of large. Large usually means >=7B parameters (2023). If it's less,…
albertzeyer on HN
Tools shown do not appear to be language models or run in browser
From 2 comments
Which one of these is an LLM? The youtube summary one maybe? Doesn't seem to run in the browser.
TOMDM on HNThese aren't LLMs...
supermatt on HN
Lacks explanation of what the site does and how it runs
From 1 comment
You should have some text explaining what is going and how they are running locally on the GPU - otherwise everyone sharing the link will need to write an explanation of why…
anigbrowl on HN
Requests
Add a roughly 1B parameter LLM for the browser
From 1 comment
Nice, whats the text to video model? Also, you could try to go for a 1b llm for the browser, would fit.
senseiV on HN
Add more explanation and model details
From 2 comments
You should have some text explaining what is going and how they are running locally on the GPU - otherwise everyone sharing the link will need to write an explanation of why…
anigbrowl on HNThe name "Tiny LLMs" does not make sense. LLM stands for large language model. So tiny is kind of the opposite of large. Large usually means >=7B parameters (2023). If it's less,…
albertzeyer on HN
Questions
What is Mistral 1B and is it supported
From 2 comments
What’s Mistral 1B? I only know of Mistral 7B.
woadwarrior01 on HNThe announcement seems somewhat disingenuous. The PR[1] found from their release notes[2] seems to contain only boilerplate and no real support for Mistral models or their…
woadwarrior01 on HN
Which tool on the site is an LLM
From 1 comment
Which one of these is an LLM? The youtube summary one maybe? Doesn't seem to run in the browser.
TOMDM on HN
Alternatives named
WebLLM browser chat demo
From 1 comment
Here is an actual LLM that runs in the browser: https://webllm.mlc.ai/#chat-demo I cannot make this work on Chrome in Linux. I even tried with…
ilaksh on HN
Ermine.ai and Google TensorFlow.js speech toolkit
From 1 comment
The speech recognition tool is impressive! I've tried many different attempts at browser-local speech-to-text from Ermine.ai to Google's Tensorflow.js speech toolkit (recognition…
jackconsidine on HN