650 AI Lab
650 AI Lab
  • 192
  • 666 829
h2ogpt: Another Open-source large language model by H2O.ai team
Another full open source large language model from H2Oa.o AI team with 12B and 20B parameters, trained on the Pile open-source dataset is released with the following features:
- Open-source repository with fully permissive, commercially usable code, data and models
- Code for preparing large open-source datasets as instruction datasets for fine-tuning of large language models (LLMs), including prompt engineering
- Code for fine-tuning large language models (currently up to 20B parameters) on commodity hardware and enterprise GPU servers (single or multi node)
- Code for enabling LoRA (low-rank approximation) and 8-bit quantization for memory-efficient fine-tuning and generation.
- Code to run a chatbot on a GPU server, with shareable end-point with Python client API
- Code to evaluate and compare the performance of fine-tuned LLMs
== Video Timeline ==
(00:00) Content Intro
(00:15) Introducing H2O
(01:30)H2O.ai Intro
(03:05) h2ogpt
(04:55) h2ogpt Chatbot
(09:35) h2ogpt Details
(10:40) H2O llmstudio Intro
(13:20) Conclusion
=== Resources ===
- h2o.ai/
- h2o.ai/events/h2o-world/
- github.com/h2oai/h2ogpt
- github.com/h2oai/h2o-llmstudio
- huggingface.co/spaces/h2oai/h2ogpt-chatbot2
- huggingface.co/spaces/h2oai/h2ogpt-chatbot
- www.kaggle.com/code/philippsinger/openassistant-conversations-dataset-oasst1
Please visit:
prodramp.com | @prodramp
www.linkedin.com/company/prodramp
Content Creator:
Avkash Chauhan (@avkashchauhan)
www.linkedin.com/in/avkashchauhan
Tags:
#stablelm #stableai #finetunellm #openai #python #ai #langchain #chromadb
มุมมอง: 3 463

วีดีโอ

StableLM: An Opensource large language model by Stability AI team
มุมมอง 913ปีที่แล้ว
Another full open source large language model from Stability AI team with 3B and 7B parameters, trained on The Pile Datasets and fine tuned on 5 other conversational datasets - Stanford's Alpaca, Nomic-AI's gpt4all, RyokoAI's ShareGPT52K datasets, Databricks labs' Dolly, and Anthropic's HH Video Timeline (00:00) Content Intro (00:35) Introducing StableLM (01:19) StableLM Model Intro (03:03) Qui...
Bringing LLM to the Enterprise (training from scratch or just fine-tune) with Cerebras-GPT
มุมมอง 1.6Kปีที่แล้ว
So you want to utilize LLM for your enterprise and don't know where to get started? This video is exactly for you. In this video you will learn how to utilize Cerebras open-source LLMs for your own enterprise consumption either training from scratch or just fine-tune on your enterprise data and everything around that... Video Timeline (00:00) Content Intro (00:54) Introducing Cerebras-GPT (04:0...
Dreamix - Applying Video Diffusion Models as General Video Editors (AI-fused Video Editing)
มุมมอง 491ปีที่แล้ว
Dreamix: Video Diffusion Models are General Video Editors Dreamix can create videos based on image and text inputs. In this example it is able to instill complex motion in a static image, adding a moving shark and making the turtle swim. In this case, visual fidelity to object location and background was preserved but the turtle direction was flipped. Given a small collection of images showing ...
Instruct-NeRF2NeRF - Combining Diffusion Models with NeRF to create new NeRF Objects
มุมมอง 2.5Kปีที่แล้ว
Instruct-NeRF2NeRF enables instruction-based editing of NeRFs via a 2D diffusion model Resources and Source Code GitHub : - instruct-nerf2nerf.github.io/ - github.com/prodramp/DeepWorks/blob/main/nerf/README.md - github.com/prodramp/DeepWorks/blob/main/nerf/Instruct-NeRFNeRF.md ▬▬▬▬▬▬ ⏰ TUTORIAL TIME STAMPS ⏰ ▬▬▬▬▬▬ - (00:00) Instruct-NeRF2NeRF Introduction - (01:53) 3 Ways to use Instruct-NeRF...
Whiteboarding - Large Language Model (LLM) Tech Stack
มุมมอง 1.3Kปีที่แล้ว
In this white-boarding session you will learn: - LLM In General - LLM Models accessible through API only - Open LLM Models (can be downloaded and hosted) - Summary The screenshots at GitHub: - github.com/prodramp/DeepWorks/blob/main/ChatGPT/Whiteboarding-LLM-TechStack.md Video Timeline (00:00) Content Intro (00:14) LLM Models (02:08) LLM Models from API (08:35) Self hosted LLM (11:05) ChatGLM-6...
Whiteboarding - Let's understand ChatGPT
มุมมอง 894ปีที่แล้ว
In this white-boarding session you will learn: - What is ChatGPT - The Role of GPT - ChatGPT training steps The screenshots at GitHub: - github.com/prodramp/DeepWorks/blob/main/ChatGPT/Whiteboarding-ChatGPT-Intro.md Video Timeline (00:00) Content Intro (00:47) What is ChatGPT? (05:20) Understanding GPT Models (10:24) ChatGPT Training (15:00) Recap Resources - github.com/chroma-core/chroma - git...
Beginners workshop to fine-tune OpenAI LLM model with enterprise web data in Python
มุมมอง 4.3Kปีที่แล้ว
This hands-on workshop shows how to use Langchain LLM application framework with Chroma embedding database to fine-tune an OpenAI GPT-3.5-Turbo LLM model on web data. The final solution returns ChatGPT like interface to your customer web data. You will also learn: - Why it is important to fine-tune LLM models with ad-hoc data - How to use open-source libraries i.e Langchain, ChromaDB The worksh...
Python Gradio UI for Fine-tuning LLM (OpenAI GPT) with Custom Data
มุมมอง 4.4Kปีที่แล้ว
This video is hands-on-lab to create a python application using Gradio UI to fine-tuning OpenAI LLM model with llamaindex (or gpt-index) library. Fine-tuning LLM: LLM can be extended, by fine tuning with custom dataset to provide Q&A, summary and many other ChatGPT like functions. In this video, we are using LlamaIndex (GPT Index) which provides a central interface to connect your LLM's with ex...
Fine Tuning LLM (OpenAI GPT) with Custom Data in python
มุมมอง 14Kปีที่แล้ว
LLM can be extended, by fine tuning with custom dataset to provide Q&A, summary and many other ChatGPT like functions. In this video, we are using LlamaIndex (GPT Index) which provides a central interface to connect your LLM's with external data. Full code discussed in the video can be found here: - github.com/prodramp/DeepWorks/blob/main/ChatGPT/FineTuneLLM.md Video Timeline (00:00) Content In...
Modern and Postmodern Data Stack (Architecture and why you need it?)
มุมมอง 376ปีที่แล้ว
This video discussed the following topics: - Modern Data Stack - What is it? - Postmodern Data Stack - Why you need Postmodern Data Stack Video Timeline (00:00) Content Intro (00:58) Part 1 Review (01:52) Need for MDS (02:18) Moden Data Stack Intro (04:34) Modern Data Stack Features (07:25) Postmodern Data Stack - Why? (11:25) Postmodern Data Stack - Architecture (16:45) Conclusion Please visit...
Data Engineering and Storage Concepts (With ETL, ELT, Warehouse, Lake and Lake House)
มุมมอง 563ปีที่แล้ว
This video discussed the following topics: - Data Stack (Modern and Post-Modern) - Data Storage and Analysis - Data Lake, Data Warehouse, Lake House - ETL, ELT, and when to use it - Data Transformation and Pipeline - Data Mesh Video Timeline (00:00) Content Intro (00:17) What is answered? (01:45) Part 1 Content (03:05) Data Storage and Analysis (06:25) Data Warehouse (08:30) Data Lake (10:08) L...
Develop Successful Deep Learning Projects with this 10 Steps formula
มุมมอง 444ปีที่แล้ว
Following are the 10 steps you can follow for a Deep Learning project success. 1. Understand & Define The problem: Understand the problem first and then define it clearly and you are ready now 2. Prepare your data: It’s all about your data, make sure it ready for the real problems 3. Choosing right method: You will not get it right at first time, still you need something to be on right track 4....
Stability AI plugin for Blender - Create images, texture and animations
มุมมอง 3.2Kปีที่แล้ว
Stability for Blender is released for public to use the Stability SDK inside Blender. With no dependencies to install and no GPU required, Stability for Blender lets you add AI post-processing effects to your renders with just an internet connection - something that previously required owning prohibitively expensive hardware. You must need dreamstudio account and API key to make this plugin wor...
Ubuntu 22.04 Kernel (6.2.1) Update with latest Nvidia Display Driver (525.89.02)
มุมมอง 3.8Kปีที่แล้ว
This video covers the following two concepts: [1] Ubuntu 22.04 Kernel Update (from 5.19.x to 6.2.1) using mainline [2] Latest Nvidia Display Driver installation and (update) of on Ubuntu 22.04 machines Here are the main topics in this video: [1] Install mainline (Add cappelikan Repo) [2] Update Kernel from 5.19.x to 6.2.1 (latest Feb 25) (Using the mainline application) [3] Identify problems wi...
Nvidia Display Driver (525.89.02) Installation (and update) on Ubuntu 22.04
มุมมอง 10Kปีที่แล้ว
Nvidia Display Driver (525.89.02) Installation (and update) on Ubuntu 22.04
Video to Video Creation with GEN-1 AI Model and the power of Generative AI
มุมมอง 599ปีที่แล้ว
Video to Video Creation with GEN-1 AI Model and the power of Generative AI
Creating Deep Learning study plan with Mindmap using ChatGPT
มุมมอง 5Kปีที่แล้ว
Creating Deep Learning study plan with Mindmap using ChatGPT
Prompt Engineering - Understanding Large Language Models with ChatGPT
มุมมอง 2.9Kปีที่แล้ว
Prompt Engineering - Understanding Large Language Models with ChatGPT
Meet Claude - Anthropic Large Language Model similar to ChatGPT
มุมมอง 1.5Kปีที่แล้ว
Meet Claude - Anthropic Large Language Model similar to ChatGPT
How ChatGPT can improve your career & professional prospects and land a new job?
มุมมอง 755ปีที่แล้ว
How ChatGPT can improve your career & professional prospects and land a new job?
ChatGPT: How to access through Python libraries in your code?
มุมมอง 1.3Kปีที่แล้ว
ChatGPT: How to access through Python libraries in your code?
Beginners Guide to Rust code compilation and debugging in VSCode IDE
มุมมอง 10Kปีที่แล้ว
Beginners Guide to Rust code compilation and debugging in VSCode IDE
ChatGPT on test drive teaching how to learn Rust?
มุมมอง 1.1Kปีที่แล้ว
ChatGPT on test drive teaching how to learn Rust?
Are you sure the open-source React package (from npm) is malicious/risky?
มุมมอง 466ปีที่แล้ว
Are you sure the open-source React package (from npm) is malicious/risky?
Do you know if open-source Python package in your application is malicious/risky?
มุมมอง 877ปีที่แล้ว
Do you know if open-source Python package in your application is malicious/risky?
Updating GitHub Token using a Single command
มุมมอง 2.8Kปีที่แล้ว
Updating GitHub Token using a Single command
Think object oriented programming is hard? Try these 10 steps to master in python
มุมมอง 2.9Kปีที่แล้ว
Think object oriented programming is hard? Try these 10 steps to master in python
Python Workshop with face detection, mesh & orientations with Hugging Face deployment
มุมมอง 4.3Kปีที่แล้ว
Python Workshop with face detection, mesh & orientations with Hugging Face deployment
No-Code and Full-Code Data Analytics with GigaSheet & Pandas (Side-by-Side)
มุมมอง 2Kปีที่แล้ว
No-Code and Full-Code Data Analytics with GigaSheet & Pandas (Side-by-Side)

ความคิดเห็น

  • @chhakulizingare9382
    @chhakulizingare9382 2 วันที่ผ่านมา

    I want help in the pie chart I want custom arc link labels how to do that.

  • @selfreference2
    @selfreference2 14 วันที่ผ่านมา

    If you're running Windows, the path should be something like "C:/Python311/Lib/site-packages/streamlit" and your debugger will work for Streamlit.

  • @FaisalHadiputra
    @FaisalHadiputra 22 วันที่ผ่านมา

    This tutorial helped me so much! Thank you!

  • @anonymousgawd..3047
    @anonymousgawd..3047 27 วันที่ผ่านมา

    Sir can u suggest which type of hardware is okay for deep learning rtx ddr4 ram 8gb i7 processor is okay ?or i need more adavanced system

  • @sonalikamble5929
    @sonalikamble5929 หลายเดือนก่อน

    Perfect sir

  • @OmaniGamer2023
    @OmaniGamer2023 หลายเดือนก่อน

    Is that map works with offline environment ?

  • @akankshaniranjan7005
    @akankshaniranjan7005 หลายเดือนก่อน

    Can we also use it to generate text from the tabular data?

  • @zhulili4788
    @zhulili4788 หลายเดือนก่อน

    hello, I can't understand u9=concatenate([u9,c1],axis=3). why does axis equal 3?

  • @SarveshKumarVerma-cd7kv
    @SarveshKumarVerma-cd7kv หลายเดือนก่อน

    AttributeError: module 'keras.utils' has no attribute 'generic_utils' i always got same error. how to resolve this. when using the same models as you are using.

    • @CidreRForest
      @CidreRForest หลายเดือนก่อน

      I believe this issue is regarding the version of keras

  • @user-jq1yw1ik6q
    @user-jq1yw1ik6q หลายเดือนก่อน

    Why have not I find you earlier, You are True Gem. Everyone tries to sell themselves on Social Media, but you truly share your experience to help us. Today I am going to get started with your Satelite Imagery Projecr

  • @doublesami
    @doublesami หลายเดือนก่อน

    I have few questions becuase i want to install cuda tool kit 11.7 and pytorch 1.3.x with cuda 11.7: 1 : can I installed cuda tool kit 11.7 with latest version of nvidia drivers 535 in ubuntu 20? 2: for cuda too kit installation , you have installed cuda toolkit twice , one by downloading from nvidia website and one by running command for conda , is it compulsory to install conda based toolkit as well?

  • @user-bl2er2ou8q
    @user-bl2er2ou8q หลายเดือนก่อน

    when I use you work in my window nvidia 3060 to generate image , I usually meet with the OOM problem,is there way to help? when I use pytorch to do such work, they usually use xformer to release the stress, is it a good way?

  • @motionislive5621
    @motionislive5621 2 หลายเดือนก่อน

    Would be amazing to animate nerfs

  • @Priming-AI
    @Priming-AI 2 หลายเดือนก่อน

    Estou fazendo uma maratona em seu canal, fantastico ! muito obrigado Avkash Chauhan !

  • @devikasinharollno.1866
    @devikasinharollno.1866 2 หลายเดือนก่อน

    i ama getting problem in helper_plot how i can fix it

  • @37_quratulrashid98
    @37_quratulrashid98 2 หลายเดือนก่อน

    I'm not able to load the content , it is giving me an error what am i supposed to do now?

  • @kaelthunderhoof5619
    @kaelthunderhoof5619 2 หลายเดือนก่อน

    Hi, I'm trying to make a web based virtual make up try-on. I have read about BeautyGAN and PSGAN. Can I use your Jojogan for my project?

  • @user-cm4ce5fh4q
    @user-cm4ce5fh4q 2 หลายเดือนก่อน

    THANK

  • @user-ln2ne5ok4f
    @user-ln2ne5ok4f 2 หลายเดือนก่อน

    can i finetune to using my own images and custom prompt? a typical example say i have 1000 custom images and 1000 text prompt corresponding

  • @kulsoompanhwar190
    @kulsoompanhwar190 2 หลายเดือนก่อน

    best guidlines

  • @user-dm2ik5dh1z
    @user-dm2ik5dh1z 2 หลายเดือนก่อน

    nothing is visible!

  • @zahrazamir7896
    @zahrazamir7896 2 หลายเดือนก่อน

    Aoa sir, can you tell which parameters or data is used to design the model initially at the server.

  • @apoorvsadhale6865
    @apoorvsadhale6865 2 หลายเดือนก่อน

    Hello Sir, When I am using segmentation Model it is not working properly. It gives me error saying Keras engine not found

  • @CommaComa
    @CommaComa 3 หลายเดือนก่อน

    hey, can you suggest a way to find satellite images for training a deep learning model(wildfire detection)?

  • @kulsoompanhwar190
    @kulsoompanhwar190 3 หลายเดือนก่อน

    Asalamalikum, sir I have a query regarding the Deep image output , when there were coordinates on earth how we present those values with map

  • @user-ty8ht5pf9u
    @user-ty8ht5pf9u 3 หลายเดือนก่อน

    Thank you. This command is useful for developers.

  • @Katriya_entertainments-rj1fn
    @Katriya_entertainments-rj1fn 3 หลายเดือนก่อน

    Hello Sir If you can suggest some tutorial on how to create these multi label mask images for satellite data, that will be very helpful.

  • @Dynamic_maps
    @Dynamic_maps 3 หลายเดือนก่อน

    Genuis

  • @dvidsvijdsvijodsvijdsv
    @dvidsvijdsvijodsvijdsv 3 หลายเดือนก่อน

    all your huggingface spaces are currently showing runtime errors

  • @mohammedsaifuddin7040
    @mohammedsaifuddin7040 3 หลายเดือนก่อน

    Tip, when you explain things on Jupyter Notebook, at least zoom it. Thanks.

  • @Game-On1080
    @Game-On1080 4 หลายเดือนก่อน

    Sir, can i use my laptop GPU to generate the images

  • @neville361
    @neville361 4 หลายเดือนก่อน

    Blender is transparent after I have installed it? The PC screen, icons, background, etc are visible through Blender?

  • @lucasgoiana
    @lucasgoiana 4 หลายเดือนก่อน

    Would you help me downloading the images ? It seems like there is no available link in the website provided

  • @mohamadilhamfahrizisofyan5087
    @mohamadilhamfahrizisofyan5087 4 หลายเดือนก่อน

    when i try the command plt.figure(figsize=(14, 5)) librosa.display.waveshow(music_array2, alpha=0.1) plt.vlines(beat_times, -1, 1, color='r') plt.ylim(-1, 1) it says : process_plot_var_args' object has no attribute 'prop_cycler' can you help mee?

  • @Naruto-gi5zn
    @Naruto-gi5zn 4 หลายเดือนก่อน

    How can I contact you sir

  • @Naruto-gi5zn
    @Naruto-gi5zn 4 หลายเดือนก่อน

    Sir a small trouble we cannot download the stylegan2.-ffhq-config-f.pt files from the urls could you please make a reply for this

  • @dineshkumarm-rz5yd
    @dineshkumarm-rz5yd 4 หลายเดือนก่อน

    I am getting Jaccard coef in larger range like 455432.12 and all , what is the issue

  •  4 หลายเดือนก่อน

    can i do the same with drone arial imagery ?

  • @app8414
    @app8414 4 หลายเดือนก่อน

    Thank you so much. As a dyslexic thinker and learner, this is the way forward for everyone.

  • @wakeupsahitya
    @wakeupsahitya 4 หลายเดือนก่อน

    Sir could you please tell how can I set the color pallette for LIME

  • @kangmufqi7279
    @kangmufqi7279 4 หลายเดือนก่อน

    are you using colab pro?

  • @nurainigama
    @nurainigama 5 หลายเดือนก่อน

    thank you are an inspiration

  • @ManishKumar-pb9gu
    @ManishKumar-pb9gu 5 หลายเดือนก่อน

    thank you so much for this information such a nice tutorials i ever seen thank you so much

  • @tamizhelakkiya
    @tamizhelakkiya 5 หลายเดือนก่อน

    hi, it is very useful..is it mandatory to install anaconda in the base and cuda toolkit in the new environment(in your video it is in dl39).

  • @user-nt1zq5so5g
    @user-nt1zq5so5g 5 หลายเดือนก่อน

    1.24.44 - th code wiil be work if use "karate_directed_graph.nodes" - it's work for 2.4 and older NetworkX version

  • @ScreamingBanchie
    @ScreamingBanchie 5 หลายเดือนก่อน

    can it translate English audio into Spanish text?

  • @wellhellothere1785
    @wellhellothere1785 5 หลายเดือนก่อน

    nvcc -V and nvidia_smi return that I have cuda Built on Wed_Nov_22_10:17:15_PST_2023 Cuda compilation tools, release 12.3, V12.3.107 Build cuda_12.3.r12.3/compiler.33567101_0 and for the nvidia_smi cuda version 12.3 and Driver Version: 545.23.08 but when I run torch.cuda.is_available() I get false tried version 12.3.0 and 12.3.3 in the website of anaconda any idea why ?

  • @hewramanwaran6444
    @hewramanwaran6444 5 หลายเดือนก่อน

    Thank you very much for your excellent explanation.

  • @user-xs7yd6qk6m
    @user-xs7yd6qk6m 5 หลายเดือนก่อน

    Great step-by-step video, which gives a functional setup. Thank you !

  • @roitai-dev
    @roitai-dev 5 หลายเดือนก่อน

    Thank you so much professor.