zlacker

[return to "Fine-tune your own Llama 2 to replace GPT-3.5/4"]
1. ronyfa+wk[view] [source] 2023-09-12 18:29:55
>>kcorbi+(OP)
For translation jobs, I've experimented with Llama 2 70B (running on Replicate) v/s GPT-3.5;

For about 1000 input tokens (and resulting 1000 output tokens), to my surprise, GPT-3.5 turbo was 100x cheaper than Llama 2.

Llama 7B wasn't up to the task fyi, producing very poor translations.

I believe that OpenAI priced GPT-3.5 aggressively cheap in order to make it a non-brainer to rely on them rather than relying on other vendors (even open source models).

I'm curious to see if others have gotten different results?

◧◩
2. halfli+6o[view] [source] 2023-09-12 18:38:22
>>ronyfa+wk
I don't think translation is a great use case for ChatGPT and LLAMA. These models are overwhelmingly trained on English, and LLAMA2 which should have more data from other languages is still focused on languages w/ Latin/Cyrillic characters (so won't work well for Arabic, Hebrew, or CJK languages).

You're better off using models specialized in translation; General purpose LLMs are more useful when fine-tuning on specific tasks (some form of extraction, summarization, generative tasks, etc.), or for general chatbot-like uses.

◧◩◪
3. famous+301[view] [source] 2023-09-12 20:44:02
>>halfli+6o
>You're better off using models specialized in translation

For a couple dozen languages, GPT-4 is by far the best translator you can get your hand on so basically no.

◧◩◪◨
4. daniel+p61[view] [source] 2023-09-12 21:08:23
>>famous+301
I will say that GPT-4 is just incredibly expensive. For my app I only use it for advanced translations/corrections, and usually a combination of GPT-3.5+Wiktionary is able to get the more simple stuff done
◧◩◪◨⬒
5. all2+hh1[view] [source] 2023-09-12 21:53:53
>>daniel+p61
> GPT-3.5+Wiktionary

Can you share more about your app and what you're doing?

◧◩◪◨⬒⬓
6. daniel+3m1[view] [source] 2023-09-12 22:18:41
>>all2+hh1
Sure! I'm building a personalized AI language learning tutor using Open AI's API and ElevenLabs (for Text to Speech).

Right now it's basically a chat bot that you can use to practice conversing with. It provides corrections for the things you type. Eventually I'd like to try adding Whisper as well to allow users to speak out loud.

When you hover over a word, you get a translation. Initially I thought using Open AI for every word translation would be too much, but I've been able to get it down to ~36-40 tokens/request. (3-4 cents/1000 requests). I also began parsing and uploading some of this [Wiktionary data](https://kaikki.org/dictionary/rawdata.html) and am working on a feature that integrates the GPT-3.5 translation with this Wiktionary data.

A lot of these features are still in the works but you can feel free to try it if you like (https://trytutor.app).

[go to top]