farouqaldori

Yes, the Tea app inspired me to write this actually

That's true when looking solely at fine-tuning costs. In theory, you could fine-tune a model locally and only cover electricity expenses. However, we provide a complete end-to-end workflow that simplifies the entire process.

Once a model is fine-tuned, you can run inference on Llama 3.2 3B for as low as $0.12 per million tokens. This includes access to logging, evaluation, and continuous dataset improvement through collaboration, all without needing to set up GPUs or manage the surrounding infrastructure yourself.

Our primary goal is to provide the best dataset for your specific use case. If you decide to deploy elsewhere to reduce costs, you always have the option to download the model weights.

Which part of the pricing seems high, platform or token pricing? Both?

About Gemini Flash, we add new model providers entirely based on feedback. Gemini is next on the roadmap!

Yes for sure. But your mileage may vary, and it all depends on the quality of the dataset that you build up.

Happy to discuss this in detail, how do you measure performance?

Yes, it's outdated. Thanks for the feedback. 4o-mini is the new king for sure!

We are working on a dedicated pricing page with all relevant information. Pricing in docs is just temporary. With that being said, new users get free credits to try out the platform without spending anything.

We've built the platform primarily for companies that serve LLMs in production, so even if we allowed you to fine-tune on device, sooner or later you will find yourself in a position where you want to deploy the model.

We want to streamline this whole process, end-to-end.

With that being said, I do agree that we shouldn't store everything on the cloud, this is what we're doing about it:

1. Any data in FinetuneDB like evals, logs, datasets etc. can be exported or deleted.

2. Fine-tuned model weights for OS models can be downloaded.

3. Using our inference stack is not a requirement. Many users are happy with only the dataset manager (which is 100% free).

4. We are exploring options to integrate external databases and storage providers with FinetuneDB, allowing datasets to be stored off our servers

Thanks for the feedback! More than happy to learn more about your workflow if you'd like to share ([email protected])

Thank you so much!

1. Where exactly did you see this? There are internal FinetuneDB API keys, and external API keys like OpenAI. Though it's confusing, I agree!

2. Work in progress.

3. I agree, thanks for the feedback.

There are multiple components working together, so it's hard to define a single tech stack. When it comes to the web app, Remix is my framework of choice and can highly recommend it.

The magic behind NotebookLM can't be replicated only with fine-tuning. It's all about the workflow, from the chunking strategy, to retrieval etc.

For a defined specific use-case it's certainly possible to beat their performance, but things get harder when you try to create a general solution.

To answer your question, the format of the data depends entirely on the use-case and how many examples you have. The more examples you have, the more flexible you can be.

Ah I see, got it. For now the API should work fine for that!

We don't support Codestral or Qwen2.5-coder right out of the box for now, but depending on your use-case we certainly could add it.

We utilize LoRA for smaller models, and qLoRA (quantized) for 70b+ models to improve training speeds, so when downloading model weights, what you get is the weights & adapter_config.json. Should work with llama.cpp!

There hasn't been a significant demand for the Python SDK yet, so for now we suggest interacting with the API directly.

With that being said, feel free to email us with your use-case, I could build the SDK within a few days!

Hey all, co-founder here happy to answer any questions!

I'm the co-founder & CTO at www.finetunedb.com - and before launching FinetuneDB, I founded a genai app in the application layer (visus.ai) where I built my own in-house testing toolkit.

No matter if you build or buy, what you want to achieve is the following:

1. Visibility over what's going on in production. 2. Ability to identify both good and bad outputs. 3. Performance measuring (custom evaluations). 4. Feedback loop with fine-tuning.

With those pieces in place, you can start making data-driven decisions.

What we've learned so far is that each application is unique, so if you could tell me more about your app I could share some insights.

I don't necessarily mistrust Chinese SaaS products, though I find Chinese products to follow a design paradigm that is outdated from a UI/UX perspective.

Also, in general, Chinese products tend to be slow which is understandable if the servers are located in China.

Hey!

How many hours does Samantha work for you on a monthly basis, and how often do you publish?

Well, that's underwhelming! Expected some serious architectural design.

Cool component nonetheless, makes sense that it's fake since the majority of users wouldn't bat an eye.

The awful readability of that website must be satire, right?

There isn't any resemblance to Travis Scott besides the obvious "It's lit"-adlibs to be honest.

I loved the parts where they showed some PHP echoing some HTML to give the video that hacker vibe.