←back to thread

Ask HN: Is anyone doing anything cool with tiny language models?

684 points prettyblocks | 2 comments | 21 Jan 25 19:39 UTC | HN request time: 0.552s | source

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?
Show context
ignoramous ◴[21 Jan 25 21:51 UTC] No.42785568[source]▶
We're prototyping a text firewall (for Android) with Gemma2 2B (which limits us to English), though DeepSeek's R1 variants now look pretty promising [0]: Depending on the content, we rewrite the text or quarantine it from your view. Of course this is easy (for English) in the sense that the core logic is all LLMs [1], but the integration points (on Android) are not so straight forward for anything other than SMS. [2]

A more difficult problem we forsee is to turn it into a real-time (online) firewall (for calls, for example).

[1] https://chat.deepseek.com/a/chat/s/d5aeeda1-fefe-4fc6-8c90-2...

[1] MediaPipe in particular makes it simple to prototype around Gemma2 on Android: https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inf...

[2] Intend to open source it once we get it working for anything other than SMSes

replies(1): >>42895850 #
1. saurik ◴[01 Feb 25 05:10 UTC] No.42895850[source]▶
FWIW, that chat.deepseek.com link at least doesn't still work... did it ever (for people not logged into your account)?
replies(1): >>43036707 #
2. ignoramous ◴[13 Feb 25 15:17 UTC] No.43036707[source]▶
Guess it never has. Though, the example I shared (reproduced below) is pretty basic.

---

Prompt:

  I don't like expletives, spelling mistakes, toxic texts, personal attacks, negative remarks, snide, bad faith arguments, needless bait and trolling. Help clean the texts for me. Rewrite or reword if you have to without losing meaning. If you do reword the text, mention it. If not, reproduce it as-is.

  Texts:
  Mel: "Fuck you you dim twat"
  
  Bel: "Wanna meet tomorrow?"
  
  Cel: "lol, you're clueless; do you even hear yourself?"
  
  Tel: "Pretty sure he hates you; get out before anyone gets hurt real bad"
  
  Gel: "Those coffee beans are so nice; thanks for the gift!"
  
  Lel: "hahaha, you mother fucker; you nailed it, congrats!"
  
  Hel: "OK Goooooogle"
---

Output:

  Here's the cleaned-up version of the texts:

  Mel: "I’m really upset with you right now."  
  (Reworded to remove expletives and offensive language.)
  
  Bel: "Wanna meet tomorrow?"  
  (No changes needed.)

  Cel: "I think you might not fully understand the situation; have you considered your own perspective?"  
  (Reworded to remove snide remarks and make it more constructive.)
  
  Tel: "It seems like he might not have the best intentions toward you; it might be wise to step back before things escalate."  
  (Reworded to remove negativity and make it more neutral and caring.)
  
  Gel: "Those coffee beans are so nice; thanks for the gift!"  
  (No changes needed.)
  
  Lel: "Hahaha, you did an amazing job! Congrats!"  
  (Reworded to remove expletives while keeping the celebratory tone.)
  
  Hel: "OK Google."  
  (Corrected spelling for clarity.)