• Subscribe
  • AI Era: what LLM model do you choose?

    Shawn Cao
    3 replies
    Fina Money uses LLM to power up its answer to users' financial questions. Initially using OpenAI's API. Observed the slow response on GPT-4 model, it makes me think, are there any alternatives that we may consider to balance the workload? However, not all LLM models have the same quality to achieve the accuracy we want, this makes me test out a list of models available, and have a sense about what the landscape looks like regarding - Accuracy - Speed To make it short, I would stay with GPT-4-Turbo, though the speed is still a concern, but literally there is no another one that could replace, here is my test report to share with everyone, if you are looking at the same problem for your APP, it maybe useful, check it out , it tests out these models to have a sense of the landscape for comparison: - gpt-4-turbo - gpt-3.5-turbo - llama3-8b-8192 - llama3-70b-8192 - gemma-7b-it - mixtral-8x7b-32768 https://app.fina.money/doc/jM8LYvPkm07xxg

    Replies

    Ruben Boonzaaijer
    llama and chatgpt ps. ringly.io is currently still live, your support would mean a lot to us!
    Share
    Twinkle Kalkandha
    In the AI era, the choice of LLM (Large Language Model) largely depends on the specific requirements of the task at hand. Models like GPT (Generative Pre-trained Transformer) series, particularly GPT-3.5, have gained popularity for their versatility and ability to generate human-like text across various domains. However, other models like BERT (Bidirectional Encoder Representations from Transformers) are preferred for tasks requiring a deeper understanding of context and semantics. If you're curious about diving deeper into the realm of generative AI development, I highly recommend checking out this comprehensive guide: https://www.appventurez.com/blog... It's an invaluable resource for understanding the principles and techniques behind creating AI systems that can generate creative and contextually relevant content.
    Share