Видео

thanks

woah, quality of content 👌 liked and subscribed

What’s happened under the hood of DSPY, how many tokens it will use during fine tuning process? thanks

21 open tabs! I'm *not* the only one! 🙃

Great video. I'm pretty unfamiliar with cloud, I just wanna make sure that I can get a LLM to service multiple endpoints for multiple users. If so how do I get to know the number of users that can be serviced

hi sir thanks for your great work, my question is , is this considered as generative Q&A or extractive Q&A.

Yes what about costs? Any easier platforms you have tried?

What's the algorithm tho.

Why is that everyone skip the most important part of AWS service for automation which is how to create the Lambda code! Is there a resource about how to write or make the Lambda context/code?

I would rather use prompt engineering than DSPy. The beauty of LLm is to generate contents/code with natural language, now DSPy asks people to use programming lanaguage again. There is also deep learning curve for DSPy.

Any way you can make the font bigger? :)

If I want to fine tune for RFP’s document, what is the best way? Please help.

What if I have a custom model (for which I also have the model artifacts) that I want to deploy to Azure ML?

i'm trying a qa in portuguese, but the models I found on HF just returns short answers. Would you suggets any model?

In my experience the challenge is the metric function. Examples always seem to use exact match; getting a qualitative metric working is non-trivial. Try use DSPy to optimize prompting for summarizing video transcripts, for example; you'll probably spend more time trying to get the metric working than you would have just coming up with a decent prompt. You also need a metric function that is going to discriminate between prompts of different quality, which is also not as trivial as it might seem.

Bigger text would have been awesome for the notebook. Thanks for the info.

Yes, this was useful. Thank you. But after watching the video I'm still not sure if DSPy lives up to the hype. What I would want to see is a series of benchmark tests of "Before Teleprompter" and "After Teleprompter" results on a determinative set of tasks that cover a range of concerns. Such as: math questions, reasoning questions, code generation questions, categorized into Easy, Medium, Difficult. This should be done with a series of models, starting with, of course, GPT4, but including Claude, Groq, Geminia, and a set of HuggingFace Open Source models such as DeepseekCoder-Instruct-33B, laser-dolphin-mixtral-2x7b, etc. I would want to see this done with the variety of DSPy Compile options, such as OneShot, FewShot, using ReACT, and using LLM as Judge, etc., where the concerns are appropriate. In other words, a formal set of tests and benchmarkes based on the various, but not infinite, configuration options for each set of concerns. This would give us much better information and be truly valuable to those who are embarking on their DSPy journey. Right now, it is very unclear whether compiling using teleprompter actually provides more accurate results, and under what circumstances (configurations). I have seen more than one demo, and in some cases the teleprompter actually produced worse results, and the comment was "well, sometimes it works better than others". My proposed information set, laid out in a coherent format, would be tremendously useful to the community and would go a long way towards answering the question you posed: Does DSPy live up to the Hype? Because we don't have this information, the Jury is still out, and your video poses the right question, but doesn't quite answer it, tbh. The benchmarking tests I am proposing would. That along with a thoughtful discussion of the discoveries would be tremendously useful. That said, I did learn a few useful things here, and so thanks again!

Ok, i did not understand one thing. Why did you include ANSWERNOTFOUND in the context? This seems to defeat the whole purpose of getting a correct answer. How would i know if the context is relevant to the question before the question is asked? Is it not similar to data leakage? The true test would be to just remove ANSWERNOTFOUND from the context , because we don't know what question that might be asked, or we can even create negative examples like we do in word2vec and just use them to train the answernotfound. Let me know if I make sense

is there an easier way to do this with Ollama?

Good review! My issue with these frameworks is their limitations become more transparent with large and more complex use cases - the boiler plate code ends up being technical debt that needs circumventing and the next iteration of the GPT's or Mistrals intrinsically solve some of the previous limitations that the models couldn't solve for.

You haven't exaplined the code what is the preprocessing code doing how is it working ? Its a request to make a new video on proper explanaation of the code.

🎉

haha i am the 1000th subscriber :)

Extremely helpful! Thanks

@buksa7257 0 seconds ago Im having a bit trouble undestanding the following: i believe you're saying the lambda function is calling the endpoint of the sagemaker (the place where we stored the llm). But then who calls the lambda function? When is that function triggered? Does it need another endpoint?

can you run 7b model on normal i5 16gb ddr5 laptop without gpu ?

Great summary, thanks!

hey i want to contact you, how can i ?

Great explanation and prop choice 👍

Your microphone is terrible, but the video is great. Thanks. 🎉🎉❤

Texts are so small, facing difficulties

thanks a lot for sharing this with us

what's the requirements for the 30b and larger models when quantized? how much vram or system ram is needed?

Please share your laptop specifications. Mine works so slow...

sorry i did not understand which file needs to be modified for the external server and where i should look in the Lm Studio folder. thank you :-)

Amazon sagemaker is pretty complex and the ui horrible, any other ways to deploy? The compute model tried to charge me like 1000 dollars for the free usage. Because it spins up like 5 instances. Instance that don’t show up in the console directly, you have to open the separate sage maker instance viewer,

whats the memory requirement for windows 10? can it run in cpu mode?

same concept in sage maker please

what's the difference between this and oobabooga?

how do i change the chatgpt url with this?

I'm deploying a LLava model (image + text), how can I invoke that?

Would really help if you can provide an approximate cost of trying out this tutorial on AWS. Is there any info someone can share?

thanks ! Do you know how to connect it with your own data ?

great information! glad you are uploading this! but i would really appreciate if you upgraded your mic :3

LM studio is proprietary shit and should not be used when they're so many great open source alternatives

If you could show how to deploy a finetuned HF model and monetize it youll be rich

when i tried to download model and then tried to run it's not loading model on studio can you please help me with that?

how to use lm studio server as a drop-in replacement to OpenAI API? please make a video on this ASAP

Is the SAAS 100% free?

sir do the same thing with csv /excel file