วีดีโอ

It's one of the project which we can definitely add in our resume. Thank you Arjun.

Hi Arjun, Thanks for this great tutorial. I am facing one issue. hoping if you could help. I am working on a use case and as per requirement i have to use offline LLM model, hence using an offline model (mistral-7b-instruct-v0.2.Q4_K_M.gguf). I am also using crewAI to build my multiagent system. I am keep on getting this error : "Number of tokens (85083) exceeded maximum context length (32000)". 32k context window is max for model i am using. Without changing model (given i have limited resource to handle large model) what i can do to overcome this issue.. any work around you would like to suggest.? thanks and would really appreciate your response.

Hello sir I have followed your video, i started with the notebook example, however i got stuck when i run this cell [ from transformers import AutoTokenizer model_id = "mistralai/Mistral-7B-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=True) ] This is the error i am getting: Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 40 column 3 I did not change anything though. Please help me out.

Hii bro great video but can you tell me that if i upload a llama model on sagemaker and only use it through API gateway then i am going to charge for per API request i will charge for 24/7 as llm is deployed there on sage maker

hi , isn't this AR type ?

if can't market , you can't sell :)

Thank you

What's the advantage of using CrewAI vs a couple of API calls to OpenAI?

Nice work, Sir ! Very informative

project\StableVITON-master\download\VITONHD.ckpt project\StableVITON-master\output i am getting this error what to doo ?

will you please make a detailed video how you are running the program, from scratch like after cloning github repo what we have to do, and how we have to connect to output. Please!!!!!!!!!!!!🥺🥺

in the requirements, I couldn't install the triton package and its coming like this ERROR: Could not find a version that satisfies the requirement triton==2.0.0 (from versions: none) ERROR: No matching distribution found for triton==2.0.0

can ypu add api to the arxiv,ieee, nature,conferences , etc ? how to do it? how to control the number of references? and length

Great video! thank you very much! :), As another question, I've been trying to use llama 3 7b, but for some reason it seems quite large for it to fit with my data, any idea what instance might be best for llama 3 7b? and now llama 3.1 7b

Great Video

bro did u train the model first?

how can i load my finetuned model after the save please

Why have you copied all the Notebooks from Deep learning AI course, by crew AI? Try to create your own content.

Outanding twice! Best tut of its kind :) Let me buy you a coffee.

Truly helpful... but I wanted to know that i have my own custom data in the form of 2 txt files how am i supposed to fine tune them with the model. Do i need to convert them to a csv format? Or is there another way to proceed?

Outstanding! But mistral-finetune github has a different approach and in less than one hour the job is done, what are the main differences or advantages? Thanks!

How to install unstructured io as docker container ?

Can you explain what the flags repaint and unpair are? I was able to run the code. but results generated are same as previous models photos

Can you say why this is coming: Loaded model config from [None] Traceback (most recent call last): File "C:\Users\dev\Downloads\StableVITON\inference.py", line 110, in <module> main(args) File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "C:\Users\dev\Downloads\StableVITON\inference.py", line 66, in main for batch_idx, batch in enumerate(dataloader): File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\utils\data\dataloader.py", line 634, in _next_ data = self._next_data() File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\utils\data\dataloader.py", line 1346, in _next_data return self._process_data(data) File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\utils\data\dataloader.py", line 1372, in _process_data data.reraise() File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\_utils.py", line 644, in reraise raise exception ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\utils\data\_utils\worker.py", line 308, in _worker_loop data = fetcher.fetch(index) File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "C:\Users\dev\Downloads\StableVITON\dataset.py", line 245, in _getitem_ transformed_image = self.transform_crop_person( File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\albumentations\core\composition.py", line 255, in _call_ self._check_args(**data) File "C:\Users\dev\anaconda3\envs\StableVITON\lib\site-packages\albumentations\core\composition.py", line 324, in _check_args raise ValueError(msg) ValueError: Key agn is not in available keys.

superrr.. I only worry about training /fine tuning cost to LLM

Nice tutorial! Thanks for that. How would you distribute this over a multi GPU instance, which might be needed for 8x7b (Instruct or Base), for example?

what is the recommended gpu to run it on please, thaank you

Great Video! Concise and to the point 👏

👏👏👍

hello, im trying to run this but i cant get it to work without setting the CUDA visible devices. how do i do it?

can i get ur contact information

Happy Diwali!! Wonderful celebration 🎉

Happy Diwali 🎉

How does it compare with COLMAP in terms of accuracy and compute?

👏👏👏

Is amazon sagemaker free

Truly inspiring sir👍🏻 Best wishes

Really inspiring

Really nice video ... Very detailed

Detailed and well explained, Thanks for the video 👍

Excellent.

Very good attempt Arjun!

Please can you send me the code