What’s everyone using for their LLM?
Discussion
What is LLM 👀
Ask ChatGPT
Who’s ChatGPT? I rather get answer from Human here 😂😂😂😂
Good for you buddy :)
I'm using Ollama and codebooga:34b for my coding tasks. I find its really great for how I use it. Its like having stack overflow-tutor
In case you've been living under a rock and aren't just trolling, LLM is "large language model" which is the basis of ChatGPT and all the other "AI" assistants these days.
Wow…. Still don’t understand… but it’s look so cool but I am not sure what is the usecase… similar like Web3… the tech look so promising untiil you don’t know what is the different…
Dolphin llama 3 70b is great
Ollama + Llama3
I was using perplexity ai. Was really satisfied with it but they seem to be blocking my vpn. Trying out gpt4o.
gpt4o, but I am not convinced. Every now and then tells me nonsense.
Ollama. But gpt4all just had a nice update. Also LMStudio is nice.
Perplexity with Claude 3 Opus for day-to-day questions; Replit (which uses either GPT-4o or GPT-4) for development.
If I weren't using Replit for software related tasks, I would only be using Claude models.
is replit/gpt better for code? why do you use replit instead of gpt directly?
They have their own Copilot implementation and LLM chat built into the IDE, so it's a smoother workflow for me, and it's nice to only have to pay for one product to get everything. Context handling for prompts related to specific files or multiple files is also very simple; just select the files needed from a drop-down, and the LLM can analyze, edit, and drop-in code where needed and across several files. Deployment management is baked into the IDE as well (with a set amount of free cloud credits every month), and they have a mobile app, so I can code on the go whenever needed.
Conversational: Claude paid
Coding: ChatGPT or GitHub Copilot
Local: Llama3 8B abliterated (https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF)
The abliterated variants seem more capable than the originals.