this post was submitted on 13 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
 

Using and losing lots of money on gpt-4 ATM, it works great but for the amount of code I'm generating I'd rather have a self hosted model. What should I look into?

you are viewing a single comment's thread
view the rest of the comments
[โ€“] --dany--@alien.top 1 points 1 year ago (1 children)

Phind-CodeLlama 34B is the best model for general programming, and some techy work as well. But it's a bad joker, it only does serious work. Try quantized models if you don't have access to A100 80GB or multiple GPUs. 4 bit quantization can fit in a 24GB card.

[โ€“] berzerkerCrush@alien.top 1 points 1 year ago

I tried the V7, which is supposedly better than GPT4. it couldn't do the things I asked it to do, unlike GPT 4 (through Bing Chat). DeepSeek also did a couple of things, but its solutions where sometimes not ideal. It's underwhelming.

The web search engine is interesting through.