🚀 Medial just raised $500k in Pre-Series A. Tap to read the announcement. 🎉

Download App

Home

Switch theme

Blog . Feedback . Privacy
Community Guidelines

Back to feeds

Anonymous

Stealth • 9m

Hi any body using foundational models (llms) in development if you doing so are you using closed like gpt or Gemini for opensource models if you are using closed source why only that because you can save money by using opensource with low parameter models which are fineuned that does the task well same as gpts

7 replies14 likes

Replies (7)

Anonymous 3
•

Amazon • 9m

Closed-source models like GPT-4 or Gemini often lead the way in terms of cutting-edge features and performance. If your project demands state-of-the-art language understanding or multi-modal capabilities, these proprietary models might be worth the investment. However, be prepared for associated costs. But, if your project requires specialized domain knowledge or unique data, fine-tuning open-source models might be the way to go. again, if time-to-market and immediate performance are critical, consider closed-source options.

2 replies1 like

Anonymous 2

Stealth • 9m

It’s essential to strike a balance between cost and performance when choosing between closed-source and open-source models. While closed-source models like GPT or Gemini offer powerful capabilities, they often come with licensing fees. Open-source models, especially fine-tuned ones, can be cost-effective without compromising quality. Consider your project requirements and budget carefully.

1 replies2 likes

Anonymous 1

Stealth • 9m

But there are accuracy issues using open models

1 replies1 like

Recommendations from Medial

Pranjal

Stealth • 9d

I'm building a single platform that will give access to all major LLMs with a single API key. So, developers don't have to juggle between SDKs, make new accounts and pay to every provider to get the best foundational models.

0 replies4 likes

Bhavesh Agone
•

Medium • 11m

Announced today, we are collaborating as a launch partner with @Google in delivering Gemma, an optimized series of models that gives users the ability to develop with #LLMs using only a desktop #RTX GPU.

2 replies5 likes

Mukesh Jha

Stealth • 10m

Are there any data scientists here? What new ways are you using large language models (LLMs) in your everyday tasks? Do you think we should include LLM topics in data science courses? If so, what should we focus on teaching? For example: - The bas

0 replies3 likes

Uttkarsh Singh

Stealth • 7m

Google has launched the Gemini mobile app in India, will you prefer using an app or web app?

2 replies10 likes

Payal Manghnani

Stealth • 7m

In a recent educational lecture, Andrej Karpathy, one of the creators of ChatGPT, provides an introduction to Large Language Models (LLMs). LLMs are advanced technologies that can process and generate human-like text. Karpathy highlights the fut

0 replies10 likes

Vaibhav Babruwan Shingde

Stealth • 11m

Hello Guys , I am going to publish proper articles on topics like AI, Finance,Startups and different technologies etc. Today's start with : GPT Models And Uses for Startups and their examples Generative Pre-trained Transformer models (GPTs) are

7 replies10 likes

Vaibhav Babruwan Shingde

Stealth • 10m

Good Morning Everyone 🔆, Do you think that, Elon Musk's Grok Model is going to be big competition for models like GPT-4,Claude Models Sonet/Optus, Google's Gemini Model or Grok is lagging behind the competition? According to me, making a Model publ

4 replies8 likes

Yash Barnwal

Stealth • 3m

🦾AI model training comes with significant costs. This chart highlights the estimated expenses for training top AI models like Google’s Gemini 1 and OpenAI’s ChatGPT-4 in 2023. These costs, calculated using both cloud computing and amortized hardware