![Sam Witteveen](/img/default-banner.jpg)
- Видео 174
- Просмотров 4 151 691
Sam Witteveen
Добавлен 2 июн 2022
HI my name is Sam Witteveen, I have worked with Deep Learning for 9 years and with Transformers and LLM for 5+ years. I was appointed a Google Developer Expert for Machine Learning in 2017 and I currently work on LLMs and and since earlier in 2023 on Autonomous Agents.
InternLM - A Strong Agentic Model?
In this video I look at InternLM an LLM which focus on math, reasoning and being able to support function calling.
Colab: drp.li/mxJrX
Github: github.com/InternLM/InternLM
LM Deploy: github.com/InternLM/InternLM/blob/main/chat/lmdeploy.md
HF: huggingface.co/internlm/internlm2_5-7b-chat
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: drp.li/dIMes
👨💻Github:
github.com/samwit/langchain-tutorials (updated)
github.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro
01:33 Hugging Face Leaderboard
01:57 InternLM Github
03:02 InternLM: LMDeploy
04:29 InternLM: Lagent
06:36 InternLM Paper
08:29 InternLM Hugging Face Models and Datasets
08:39 InternLM on Ollama
08:54 Code Time...
Colab: drp.li/mxJrX
Github: github.com/InternLM/InternLM
LM Deploy: github.com/InternLM/InternLM/blob/main/chat/lmdeploy.md
HF: huggingface.co/internlm/internlm2_5-7b-chat
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: drp.li/dIMes
👨💻Github:
github.com/samwit/langchain-tutorials (updated)
github.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro
01:33 Hugging Face Leaderboard
01:57 InternLM Github
03:02 InternLM: LMDeploy
04:29 InternLM: Lagent
06:36 InternLM Paper
08:29 InternLM Hugging Face Models and Datasets
08:39 InternLM on Ollama
08:54 Code Time...
Просмотров: 9 950
Видео
What is an LLM Router?
Просмотров 22 тыс.День назад
In this video I take a look at a new open source framework and the accompanying paper from LMSys for helping you to automate LLM selection based on the input query. Blog : lmsys.org/blog/2024-07-01-routellm/ Github: github.com/lm-sys/RouteLLM Paper : arxiv.org/pdf/2406.18665 Models and datasets: huggingface.co/routellm 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM A...
The 4 Big Changes in LLMs
Просмотров 15 тыс.День назад
In this video I talk about some of the trends that are becoming clear for future directions in LLMs and how you should be thinking about them if you plan to develop LLM apps or Agents. 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00...
Gemma 2 - Local RAG with Ollama and LangChain
Просмотров 12 тыс.День назад
In this video I go through setting up a basic fully local RAG system with Ollama 2 and the new Gemma 2 model. Code : github.com/samwit/langchain-tutorials/tree/main/2024/gemma2_local_rag Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 ...
Gemma 2 - Google's New 9B and 27B Open Weights Models
Просмотров 14 тыс.День назад
Colab Gemma 2 9B: drp.li/6LuJt 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials
Florence 2 - The Best Small VLM Out There?
Просмотров 12 тыс.2 дня назад
There is a new VLM on the scene and it comes with a dataset of 5Billion labels. The new model can do a variety of old world tasks like bounding boxes and segmentation along with newer LLM style captioning etc. Paper: arxiv.org/pdf/2311.06242 HF Spaces Demo: huggingface.co/spaces/gokaygokay/Florence-2 Colab : drp.li/fGyMm 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM...
Claude 3.5 beats GPT4-o !!
Просмотров 14 тыс.14 дней назад
In this video I examine Anthropic's latest version of theirClaude model Sonnet 3.5. I look at what the model can do and their new UI system called Artifacts. Blog: www.anthropic.com/news/claude-3-5-sonnet 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ...
How to save money with Gemini Context Caching
Просмотров 6 тыс.14 дней назад
Context Caching is a great to get your Gemini calls to cost less and be faster for many people Colab : drp.li/L7IgU 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 00:14 Google Developers Tweet 01:41 Context Caching 04:03 Demo
Mesop - Google's New UI Maker
Просмотров 59 тыс.14 дней назад
Colab Getting Started: drp.li/l1j9i Colab LangChain Groq: drp.li/k0huj GitHub: github.com/google/mesop Documentation: google.github.io/mesop/ 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 01:24 Mesop Website 02:34 Mesop Demo...
Nemotron-4 340B - Need to Make a LLM Dataset?
Просмотров 10 тыс.21 день назад
In this video, I talk about the new Nemotron model from Nvidia and how it goes beyond just one video to be a whole family of models that allows you to make endless amounts of free synthetic data to train your own language models Blog: blogs.nvidia.com/blog/nemotron-4-synthetic-data-generation-llm-training/ Tech Report: research.nvidia.com/publication/2024-06_nemotron-4-340b Testing the model: c...
ChatTTS - Conversational TTS Step by Step
Просмотров 7 тыс.21 день назад
Lets take a look at the new conversational TTS that has come out from 2Noise called ChatTTS and how you can sample speakers and add in voice effects to create high quality Site: chattts.com/en Colab : drp.li/GfO6B 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-t...
Qwen 2 - For Reasoning or Creativity?
Просмотров 6 тыс.21 день назад
In this video I go through the new releases from Qwen family of models and look at where they excel and where perhaps they aren't as good as other models out there. Colab: drp.li/ADevp 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00...
Testing Microsoft's New VLM - Phi-3 Vision
Просмотров 11 тыс.Месяц назад
In this video I go through the new Phi-3 Vision model and put it through it's paces to see what it can and can't do. Colab : drp.li/L8iFS HF: huggingface.co/microsoft/Phi-3-vision-128k-instruct 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ⏱️Time Stam...
5 Problems Getting LLM Agents into Production
Просмотров 12 тыс.Месяц назад
In this video I discuss 5 common problems in building LLM Agents for production 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 00:58 Reliability 02:46 Excessive Loops 04:36 Tools 07:59 Self-checking 09:22 Lack of Explainabili...
Google's RAG Experiment - NotebookLM
Просмотров 15 тыс.Месяц назад
notebooklm.google.com/ Blog Launch: blog.google/technology/ai/notebooklm-new-features-availability/ 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: drp.li/dIMes 👨💻Github: github.com/samwit/langchain-tutorials (updated) git hub.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro to NotebookLM 01:09 Google Blog post: Introduction to NotebookLM 01:30 Google...
Mastering Google's VLM PaliGemma: Tips And Tricks For Success and Fine Tuning
Просмотров 9 тыс.Месяц назад
Mastering Google's VLM PaliGemma: Tips And Tricks For Success and Fine Tuning
Mistral's new 7B Model with Native Function Calling
Просмотров 15 тыс.Месяц назад
Mistral's new 7B Model with Native Function Calling
Google I/O for Devs - TPUs, Gemma & GenKit
Просмотров 3 тыс.Месяц назад
Google I/O for Devs - TPUs, Gemma & GenKit
How Google is Expanding the Gemini Era
Просмотров 4,3 тыс.Месяц назад
How Google is Expanding the Gemini Era
Advanced Colab - How to go Beyond the Basics
Просмотров 4,2 тыс.Месяц назад
Advanced Colab - How to go Beyond the Basics
New Summarization via In Context Learning with a New Class of Models
Просмотров 10 тыс.Месяц назад
New Summarization via In Context Learning with a New Class of Models
Function Calling with Local Models & LangChain - Ollama, Llama3 & Phi-3
Просмотров 35 тыс.Месяц назад
Function Calling with Local Models & LangChain - Ollama, Llama3 & Phi-3
Creating an AI Agent with LangGraph Llama 3 & Groq
Просмотров 40 тыс.2 месяца назад
Creating an AI Agent with LangGraph Llama 3 & Groq
Llama3 + CrewAI + Groq = Email AI Agent
Просмотров 54 тыс.2 месяца назад
Llama3 CrewAI Groq = Email AI Agent
Unlock The Gemini 1.5 Pro API (+ File API )
Просмотров 11 тыс.2 месяца назад
Unlock The Gemini 1.5 Pro API ( File API )
Colab 101: Your Ultimate Beginner's Guide!
Просмотров 4,5 тыс.2 месяца назад
Colab 101: Your Ultimate Beginner's Guide!
Wow, thanks so much for this explanation!
Very useful content thank you Sam for your valuable insights into these topic areas
Very helpful, thank you so much
Is it possible to do tagging and extraction at the same time? In the context of event planning, I want the event details (tagging), as well as a list of vendor services and requirements (extraction). I have difficulty forming the class/schema
when im printing the random speaker, im only getting chinese text as output do you have any idea why?
i love this series of introduction ollama!!! a lot!!!
This is good stuff 🙌♥️
oobabooga?
Am I the only one who misses a memory module from Lagent? I'm gonna test this though ASAP
Hello Sam, Thanks to bring this wonderful model to our attention. There is just a confusion in the video between commercial usage and commercial licence: commercial usage is allowed without submitting any form, but with the Open Source licence you might need to Open Source any derivative work (ie finetuning you make for example). If you want to make non open source stuff with it (why would you😊?) you will need to submit the form to obtain a commercial licence, allowing you to do that. It is a quite classic business model in Open Source software
thats a nice SMALL model for function calling alright... appreciate you bringing it to my attention.
If each model gets a higher rating than its predecessors, when will we reach 100? Also, if I don't watch such videos, will this happen later?
Great work and excellent explanation. Thank you
mannnnnnn no china
Fun fact these Chinese models are banned in the USA and can’t be used for a commercial product
Quite an enigma how you combine an interest in rather techy stuff like tool calling LLMs with a straight off the turnip truck view of other things that seems as easy or easier to get informed about.
Fun fact: A source helps. @TheGuillotineKing seems cognitively challenged holding apart the current talks to maybe restrict the EXPORT of OSS Models vs the other way around.
@@dinoscheidt Fun Fact your mother swallowed a gallon of 🥜🥜🥜🥜🥜🐿️🐿️🐿️ juice and that's how she had you
What is the agentic aspect? Maybe I don't understand something or missed something?
He talks about it at 4:45
Thank you, Sam, for once again highlighting the most interesting new models/techniques in this fascinating field. I note InternLM 2.5 explicitly notes that it "supports gathering information from over 100 websites" with an implementation using Lagent. I'm sure a LangChain implementation could be easily created as well. Actually fine tuning models with Sources for information not in the model (like current weather or news) with function calling and JSON support and using LangChain for finer control would be a great method for using smaller local models. (I feel more comfortable using LangChain than a model specific framework, if possible.) I would love to see other models add this approach. I wonder how much this is done in pretraining vs the base model. (guess I'll have to look at the paper 😉).
Cheers to @samw over @sama. Sama is a charlatan grifter. Please can we move on from him. @samw is a much better representative and explainer of what is going on.
thanks! in spanish is regular but good that all evolution :)
ask him what happen in 1989 LOL
Do we have any idea what non-english languages are supported for llama3?
I couldn’t get InternLM to work well with RAG or any embedding. It gives ok answers to simple prompting.
thanks!!
great job mate! And this is a bit like glm4, not sure about the comparison of benchmark. Both are agentic designed, and could be trained with agentic instructions.
No matter how good chinese models are nobody's gonna believe it because the whole country is a big liar and there is no guarantee of anything and everything they produce is cheap versions of something great.. so I would stay away from anything and everything coming from china but still thanks for the video
Kind of interesting that if one of the stronger points of InternLM 2.5 is being able to support agents, I wonder what part of the training data makes it more capable of supporting agents if function calling data only accounts for 16%. Thanks for the video, I'll have to find a way to make time to try it out.
LMDeploy is a quite interesting framework to deploy and quantize most of the Chinese models. It also works in Kaggle fairly well given it supports also older GPUs.
Thanks
Nice
Thanks a lot for this I wish you could consider the continuing process for identifying authentic and fake certificates 🙏🙏🙏
Brilliantly put together points, Sam. I have been seeing them coming and clearly you’ve articulated all of them up well.
pls pls, do new videos as most of the codes show deprecated. These videos are amazing.
yeah this is close on 18 months old now. I will try to record an update soon
This makes so much sense
Requesting a vid on GraphRAG
Thank you! You chose the right examples to whet my attention. Regards.
it doesn't work very well, but it is informative.
I have a huge problem with with all solutions must be a Framework, at best this is a library or even a function. Not saying you but companies/developers.
Yeah I do feel like that about a bunch of these things. This I would look at as more of a proxy you go through.
Very helpful! Thank you! 😎🤖
Thanks for sharing your experience. I want to run this model on my computer. So I wrote Modelfile like below: ---------------------------------------------------- FROM gemma-2-9b-it-Q6_K_L.gguf TEMPLATE """ <start_of_turn>user: {{prompt}}<end_of_turn> <start_of_turn>model: """ PARAMETER stop <end_of_turn> ---------------------------------------------------- And I create model to ollama, so I ran this command ---------------------------------------------------- ollama create ollama create gemma-2-9b-it-Q6_K_L -f ~/gemma-2-9b-it-Q6_K_L/Modelfile ---------------------------------------------------- And I want to run this model, so I ran this command ---------------------------------------------------- ollama run gemma-2-9b-it-Q6_K_L:latest ---------------------------------------------------- Finally, I got an error message.... Error: llama runner process has terminated: signal: aborted (core dumped) How could you run this model on ollama? Thank you.
I'd like to see more examples of applications of LLMs.
Making a one-line call to a free, open-source Python script to save 30, 50, even 70 percent token use is also an option... github.com/jgravelle/TokenMyzer
Hey Sam ... Awesome Video... Really Helpful. Just want to know is there any mechanism for evaluating it.
Thank you so much!!
Gemini 1.5 Pro is much more expensive than 1.0 Pro at this moment. It costs 7-14 times more per mil. tokens
This is actually ery interesting. Concretely, when you use langchain and has satically linked LLMs on some custom tools, how could we redirect this from langchain directly from langchain so the routing is made afterwards ?
❤❤❤
Now that is OPEN 😮 wow. Great work!
kindly make a simple html file and use it
@matthew_berman
I guess this idea similar to CoE that SambaNova use