Comparing LLMs with LangChain

preview_player
Показать описание

In this video I look at how to compare various models to see their outputs for a variety of tasks. This is an area LangChain is currently adding to as well. Models covered include GPT-3, ChatGPT 'gpt-3.5-turbo', Flan-20B, Flan-T5-XL, Cohere-command-xl

If you have any requests for videos please let me know in the comments

My Links:

Github:
  1. Sam Witteveen
  2. OpenAI
  3. LangChain
  4. LangChain Tools
  5. python
  6. machine learning
Рекомендации по теме
Comparing LLMs with 0:17:43

Comparing LLMs with LangChain

The video shows 0:11:09

The video shows how LLM can be used to compare two docs

How Large Language 0:05:34

How Large Language Models Work

What is LangChain? 0:08:08

What is LangChain?

Talk to your 0:09:49

Talk to your CSV & Excel with LangChain

Should You Use 0:06:40

Should You Use Open Source Large Language Models?

I tested a 0:17:27

I tested a STACK of FREE Large Language Models...here's how it went.

LangChain & GPT 0:05:52

LangChain & GPT 4 For Data Analysis: The Pandas Dataframe Agent

LLM Observability and 1:02:29

LLM Observability and Evaluation using Phoenix

Introduction to large 0:15:46

Introduction to large language models

Exploratory Data Analysis 0:37:41

Exploratory Data Analysis Using LLM and LangChain

02 - Exploring 0:15:48

02 - Exploring and comparing different LLM types

Vector Search RAG 1:11:47

Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search

Vector databases are 0:03:22

Vector databases are so hot right now. WTF are they?

This new AI 0:04:37

This new AI is powerful and uncensored… Let’s run it

LangChain Crash Course 1:05:30

LangChain Crash Course for Beginners

Development with Large 2:02:54

Development with Large Language Models Tutorial – OpenAI, Langchain, Agents, Chroma

Vector Databases simply 0:04:23

Vector Databases simply explained! (Embeddings & Indexes)

LangChain Agents - 0:13:34

LangChain Agents - Joining Tools and Chains with Decisions

What are Large 0:05:30

What are Large Language Models (LLMs)?

ChatGPT - Comparing 0:00:48

ChatGPT - Comparing 2 Documents

Building a Document-based 0:32:48

Building a Document-based Question Answering System with LangChain, Pinecone, and LLMs like GPT-4.

Learn RAG From 2:33:11

Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer

BERT and GPT 0:02:58

BERT and GPT in Language Models like ChatGPT or BLOOM | EASY Tutorial on Large Language Models LLM

Комментарии
Автор

Really glad I stumbled upon your videos. Super high quality, informative, and helpful. I'm sure your subscriber count will be ballooning in the coming weeks and months. Great stuff!

FreestyleTraceur
Автор

At the moment because I am a beginner I focus only on the GPT model, but maybe in the future, I will use others. Thank you for the video.

micbab-vgmu
Автор

The most powerful, and by far the best of all these, today are Alpaca 7B and Vicuna 13B. Yes, these days innovation runs fast and frenetic in this sector.

AntonioSorrentini
Автор

What a funny video you made! I love it.

ChenXibo
Автор

Thank you for your wonderful video 👌how can I compare the performance of different finetuned LLMs based on my dataset?

sharifehfadaei
Автор

It will be great if you compared the alpaca one here as well

doctalk
Автор

What are my options If i want to compare really large LLMs?

raghadabdulrab
Автор

Alpaca 30B - 4bit quantized:

> What is the opposite of up?
Down.

> Answer the following question by reasoning step by step. The cafeteria had 23 apples. If they used 20 for lunch, and bought 6 more, how many apple do they have?
They now have 18 apples (the original 23 minus the 5 that were eaten at lunch).

> Can Geoffrey Hinton have a conversation with George Washington? Give the rationale before answering.
No, because they are not in the same time period and thus cannot communicate directly. However, if we had access to some sort of portal or device that could allow them both to be present at once then it would theoretically be possible for Geoffrey Hinton to have a conversation with George Washington.

The others were'nt good enough.

AykutKlc
Автор

Great video, do you think we can do the same evaluation for qa retrieval from a doc?

hamzakivideo
Автор

The creative task should have been done with much higher Temp than 0.1 - I think.
I see it's not easy to setup params by task (compare), but I might try this with higher Temps later.

attilavass
Автор

Hi Sam,
Thanks so much for the video. It is quite cool and funny as well. You mention a paper in there, is it a research paper? Could we get ahold of it?
Thanks so much again and all the best!

CesarAngeles
Автор

Very nice information. Giving a LLM a kind of memory is a little bit challenging. Currently I´m trying to fine tune LLaMA for text-to-sql. Then it could access the DB for previous information. The DB schema is not so easy to design, maybe some (artificial) intelligence could help :D

toddnedd
Автор

Sam thank you these LLM reviews could become Yelp for AI 😆 I have a question can you post a video about computational LLM? For example to provide an actual table of data and then have a conversation or derive insights w the LLM. Langchain have a csv agent but do others?

RedCloudServices