วีดีโอ

Yes, please make a separate video

good

Better you change the title of the video

If you can’t explain it to a kid, you didn’t get at the first place. This is by far the best practical explanation of DRL, keep up the good work!

Great 🎉

Thank you very helpful

Great video, appreciate you man👏

simple

w vid

Hmm, pretty cool idea

How can i use something like that but for creative style text generating?

Source code: github.com/VatsalBhesaniya/Customer-Support-Bot

Thank you ! I successfully fo it , got some issue related to accessing model from hugging face , then in API , over all i resolved it , and integrate Lamma model in the Google colab , thank you ❤

Thank you

please the source code

can i get source code ?

this is not working in flutter web project, using windows operating system

What is it with everyone who has a conplex flowchart calling it AI? Skyrim doesn't have AI, skyrim has a bag of quest modifiers it puts togwther to make it SEEM like it has more quests, but there's no real intelligence behind it and I bet the programmers who made it would laugh at the idea...

Superb illustration👍

Hi man,can we create ai playing MMO games ?i have different ideas,but lack technical skills..

Good to start for Web Development with Framework that allow a lot of customization. I particular see this tutorial as useful to whom is starting use Flask!!!!

Since when basic algorithms are "AI"?

plt.subplot(2,3,1) must be plt.subplot(1,3,1)

Wow

Wow, this is amazing. I now understand exactly how RAG operates thanks to your excellent explanation.

why not just add a quick SDK and then just a few more ai providers not just gemini - like what easybeam ai is doing?

I completed the 100th like. . Felt nice

Wonderful video. Thank you

As someone who works on OO Python projects/code-bases intermittently , this video is absolutely one of the best concise, easy to understand explanations and demos of OOP.

Amazing description brother!

Thanks for such a detailed explanation

Hello, why use separate files and not keep all the information in the main .py file? Also, how does the opening fknow where the file is stored in the hard drive?

Cool

how to make website for weapons

The explanation in the video is amazing, keep up the good work 👍👍

The calculations for this must be immense.

No. Mario Kart CHEATS. there's a difference.

where can i find your documentation code?

Thank you for sharing. Looking forward to know more about this technique.

Please how do you get the numeric representation of datas that you use to predict churn ?

hey i have a qn should i use ML or DL when these kind of problems statements used?

great video

Perfect! 👍👍

Absolutely the best video on the topic I've seen yet. Thank you.

TLDR

A few tips to run this as 5thf of August 2024 with Llama 3.1 8B Instruct: Next to pip install transformers add upgrade transformers: ``` !pip install transformers torch accelerate bitsandbytes !pip install --upgrade transformers ``` This is the full import section: ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, AutoConfig, pipeline from huggingface_hub import login ``` Hugging Face Login, modelid and config: ``` login(token=hf_token) model_id = 'meta-llama/Meta-Llama-3.1-8B-Instruct' bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4', bnb_4bit_compute_dtype=torch.bfloat16 ) tokenizer = AutoTokenizer.from_pretrained(model_id) tokenizer.pad_token = tokenizer.eos_token config = AutoConfig.from_pretrained(model_id) config.rope_scaling = { "type": "linear", "factor": 8.0 } # Adjust the factor as needed model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map='auto') ``` Text generator: ``` text_generator = pipeline( 'text-generation', model=model, tokenizer=tokenizer, max_new_tokens=512, ) ``` Everything else can stay the same Also, go to Runtime -> Change runtime type and select the GPU option. And don't forget to ask for access to Llama on hugging face. It won't work if you're not approved.

I think you missed defining of access token here : model = AutoModelForCausalLM.from_pretrained( model_id, quantization_config=bnb_config, device_map="auto", token=accessToken )

What techniques are available for measuring coherence, relevance, and fluency in the output refinement of the generator steps?

Could you please share the colab link ?

Interesting