Відео

Is there any technique with which we can train the DSPy with our own custom question-answer examples? In video only evaluation part is covered

Hey, can you explain how to create vector embedding of video with contain visuals and voice with towhee AI or anything else?

Thank You Bro For this Video .

Sir I have a first year college capstone project of creating a book recommemdation telegram bot with integarated very small size LLMs as a knowledge base of the bot given user's inputs and predefined queries. Can you plz guide me how can this be done?

Great!

FSDP and DDP with pytorch for distributed parallel execution

Able to load quantized model through ollama create model file. In code if i want to use quantized.bin are there any steps.

Is this frame work work for others llm bye changing it's model path

Can you please tell from where we get this frame work code like any document

Its good

How is this better than using f-strings and then manage the logic in functions?

where to find api_key?

Need to try this carefully. If I get it run will update here again. But Nvidia drivers wiimore space is needed. At present I m doing on windows CPU version.

Hello sir, It's really great. You have explained from scratch I believe. This is with mistral7b text generator. I have been trying with similar steps that shown in jupyter notebook for 22b model generates code. With transformers using AutoTokenizer, AutoModelCasualLM. It's really big 44gb , 9 shards. Cache, snapshot, symlinks all are same. Later I created pipeline which was throwing error. I WAS just stuck there. Not sure why pipeline was throwing error.

Since you are only using LLMs with cuda, you can just enable the "cuda" and "langauge" features for faster compile times. It should be closer to 500 dependencies with just those two features

what is happening inside the predict how it is predicting i cant understand

Thank you. Are you able to update the video or resources given the new developments

Good content. Thank You!

Exceptional Content & Explanation. Thank You. Honestly, DSPy Documentation is extremely poor & this tutorial surely one of the best DSPy lectures.

Is there is any specific reason for using Rebel?

Thank you amazing tutorials

Hi! Firstly, thanks for sharing this video with the world! I am trying to use UnstructuredPDFLoader, which is taking about 30 minutes just to load 1 single file of 31MB. I am doing so using Google Collab and when tracking CPU usage, it is occasionally peaking at 90% or 100% although most of the time it is in the 50% region. Do you know of any way to load these PDFs at scale?

Is this free?

Hi Kamalaraj, when using the unstructured library for extracting images and text,tables from the scanned pdf files in windows. I got the error, poppler is not found and in path?. i'm installed poppler in the program files and add the path in the system variables also.. stll im getting the same error... can i install poppler in local or vs code ? please help me in this issue sir...

Thank you, the explanation was very clear and simple. I will finish the entire series.

You cannot fine tune the models using DSPy.

If I wanted to use Groq to improve the embeddings and better LLM what would be the change? And wouldn't the vector database be local to be used as RAG?

Very good

what are you running to "start the langchain server"?

can I integrate dspy with qwen72B?

Could you please tell me how can we get source documents in vector store router toolkit?

Hi sir, open ai API key is been shown will not be a problem for you if someone uses it?

Thank you sir it is an excellent playlist

Very detailed explaination. I have gone thru almost 15 videos before this. But none of them were so detailed to the point. Thank you

Great 👌

Can you help me understand, how the examples being chosen out of trainset provided in Botstrapfewshot. Also, I understand that it add rationale in the questions but like how Bootstrapfewshot works. Can you go in the code and try to gather the information, the teacher and student model, it was not clear.

Can you show the input it goes to LLM's, is it the same being shown in last videos. Well if then it is just re writing the signature in a certain way, not optimizing it or generating new one!

Hey man can't we just do all this on a docker container? Rather than getting an ec2 instance?

Could you teach me how the "trace" argument can be used to improve training? All it says on the official document is that trace is turned off during evaluation and optimization, but turned on during compiling and bootstrapping. Can trace be used to monitor the evaluation metric somehow?

Thank you for this video

Thanks! It would be really helpful if the print output cells colours are better visible.

can i add a project using pandas and fastapi to my resume? Is it a good project for resume ?

Hello, I can't find the source code of this in the github link, can you please help me out.

It's a great explanation for ollama thank you sir. But i am getting a ```{"error":"model 'llama2' not found, try pulling it first"}``` even i already pull and run the model in my server.

Hello. Can you tell me how I can persistently store the embedded data for further processing like searching?

Comprehensive, best tutorial of dspy!

Advice for future videos, don't use all caps, it's harder to read.

can you actually put mutlilple questions in a sing tavily search . So perhaps a) I want to find X b) Where is X located c) What does it work on d) What is the USP of X ?

Py is for pytorch. Great series

Hi Kamalraj, I have a question. Whats the point of using Evaluator Function ? Its not going to optimize the prompt rite.. so, its purpose is just to see how model responds to a dataset. Or , is it meant to be used again once the prompts are optimized so that we can verify whether the optimization is good or not ?