Why use this over so Ollama?
LocalLLaMA
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
LM Studio has integrated image recognition, while AnythingLLM has implemented RAG
Is it FOSS? Can you plug in any model you want?
MIT licensed and yes
It’s MIT licensed apparently
Do you know if there is openai API compatibility? More specifically I'd like to get home assistant to interact with the LLM via the custom OpenAI hacs addon
Ma qualcuno di voi è riuscito a trovare un'applicazione utile? Sarei curioso a vedere come si comporta, perché chatgpt-4 fa proprio schifo
Io ci scrivo testi formali, script bash, faccio leggergli kotlin e lo uso per analisi veloci di fatti avvenuti (quest'ultima cosa fattibile solo con gemini o gli LLM collegati al web)
La mia impressione è che va bene solo nei casi che sono talmente semplici, che dopo riesca facilmente a verificare che non ci siano errori.
Nel mio caso non trovo tanti occasioni di fare qualcosa che è più veloce rileggere e potenzialmente correggere, piuttosto che farlo da capo.
Dall'altra parte, a volte se becco un errore, invece che correggere, chiedo di nuovo e sputa una cosa abbastanza diversa.