AndriyMulyar @andriy_mulyar Twitter profile

Last Seen Profiles

@hacettepegeyikk

@FkcvU

@webcamlaxy

@relgeiz_

@getmoneyJodi

@syunsyunsyunme

@enrondripgod

@MargotF87304

@stwmaniax

@cpusa_philly

@__mika3__

@stw_pdg

@JBizzleVonSmack

@Patrioticlub

@Bokepindoo2023

@peanuts2charlie

@nom_mq

@luxexhomines

@BfEntityAvtr

@sexyassgirllll

@Jenoleh

@pengen_stw

@URSAOBIJF

@nords41

@Hunter5925

@RevistaChapman

@pengen_stw

@itssrihannaa

@tanukilaunchpad

@CandaceRaines18

@holsteincumdump

@minguinisminari

@LondynFinancial

@pengen_stw

@BfEntityAvtr

@feindura

AndriyMulyar

@andriy_mulyar

1 year

I'm excited to announce the release of GPT4All, a 7B param language model finetuned from a curated set of 400k GPT-Turbo-3.5 assistant-style generation. We release💰800k data samples💰 for anyone to build upon and a model you can run on your laptop! Real-time Sampling on M1 Mac

161

981

7K

AndriyMulyar

@andriy_mulyar

1 year

Announcing GPT4All-J: The First Apache-2 Licensed Chatbot That Runs Locally on Your Machine💥 Large Language Models must be democratized and decentralized.

84

625

3K

AndriyMulyar

@andriy_mulyar

1 year

Elite hackers have gotten gpt4all to run on a ti-84 calculator. AP calculus exams will never be the same again.

71

257

2K

AndriyMulyar

@andriy_mulyar

1 year

Talk to your documents locally with GPT4All!

GitHub - zylon-ai/private-gpt: Interact with your documents using the power of GPT, 100% privately,...

Interact with your documents using the power of GPT, 100% privately, no data leaks - zylon-ai/private-gpt

github.com

46

256

1K

AndriyMulyar

@andriy_mulyar

1 year

Gigantic Announcement for Language Models That Run on your CPU!💥📣 We are releasing: - GPT4All-Snoozy: the strongest local LLM that runs on your private CPU hardware! - The first local OS native LLM app verified by Apple ! Try it at:

71

321

1K

AndriyMulyar

@andriy_mulyar

1 year

Serious question: What does an NLP Ph.D student work on nowadays with the presence of closed source GPT models that beat anything you can do in standard academic lab? @sleepinyourhat @srush_nlp @chrmanning @mdredze @ChrisGPotts

136

199

1K

AndriyMulyar

@andriy_mulyar

1 year

Local LLMs just got 2x faster on M1/M2 Macs⚡ - Supports all LLaMA models - GPT4All exclusively supports Replit for code gen! This demo video is 13B parameters running on an M2 Macbook Pro with 16GB of RAM Run powerful, privacy-aware LLMs anywhere at

27

162

1K

AndriyMulyar

@andriy_mulyar

1 year

GPT4All and LLaMa.cpp Python Bindings Are Here 🐍💥 Over the weekend, an elite team of hackers in the gpt4all community created the official set of python bindings for GPT4all. They will be maintained for llama.cpp compatibility going forward.

GitHub - nomic-ai/pygpt4all: Official supported Python bindings for llama.cpp + gpt4all

Official supported Python bindings for llama.cpp + gpt4all - nomic-ai/pygpt4all

github.com

15

209

999

AndriyMulyar

@andriy_mulyar

1 year

Nearly a Petabyte of GPT4All Models Downloaded in 30 Days. This is why closed-sourced AI is on capital hill. They cannot win. open source will dominate in the limit.

25

175

944

AndriyMulyar

@andriy_mulyar

1 year

LLMs on edge devices without internet are the future, join us to build it.

26

80

953

AndriyMulyar

@andriy_mulyar

1 year

Very Big Announcement for Local LLM Devs💥 One line code change to use GPT4All in your existing app! Local LLMs are now compatible with a certain familiar API (and all of its software layers)

39

174

919

AndriyMulyar

@andriy_mulyar

1 year

gpt4all can now be run from any python script on CPU 🤯🚀 (kudos to elite hacker and historian @benmschmidt )

23

135

902

AndriyMulyar

@andriy_mulyar

1 year

Official GPT4All Chat UI is out 💥 The elite team of hackers has not slept all week. This UI comes built-in with features that allow you to participate in the democratic process of developing large language models.

29

162

861

AndriyMulyar

@andriy_mulyar

1 year

Chat with your data privately on CPU with GPT4All! 💥💬 -Open source - Drag and drop files into a directory that GPT4All will query for context when answering questions. - GPT4All cites its sources. Install the chat client from and go! How it works

29

118

743

AndriyMulyar

@andriy_mulyar

1 year

No. That model is not better than chatgpt3.5. false hype does a big disservice to everyone working on this Try it yourself. Open source models currently surpass chatgpt quality on small collections of individual tasks . Across the board chatgpt is a much better assistant model.

Itamar Golan 🤓

@ItakGol

1 year

I've been waiting for this 🤯 Open Source LLM Models Surpass GPT-3.5 🎉 In a groundbreaking development, a remarkable set of open-source LLM models has outperformed the capabilities of GPT-3.5. What truly amazed me is not only the exceptional performance of these models but

41

350

2K

20

46

550

AndriyMulyar

@andriy_mulyar

1 year

The GPT4All movement has been the top trending Github repository worldwide for the last eight straight days. open source the data. open source the models. gpt4all.

5

74

540

AndriyMulyar

@andriy_mulyar

1 year

Inspired by learnings from Alpaca, we carefully curated ~800k prompt-response samples to produce 430k high-quality assistant-style prompt/generation training pairs including code, dialogue, and stories. Detailed procedure for replication and data:

GitHub - nomic-ai/gpt4all: gpt4all: run open-source LLMs anywhere

gpt4all: run open-source LLMs anywhere. Contribute to nomic-ai/gpt4all development by creating an account on GitHub.

github.com

7

56

527

AndriyMulyar

@andriy_mulyar

1 year

Democratized AI Begins with Democratized Data! The GPT4All Open Source Datalake has launched!⛵💥 Find out how you can help democratize access to powerful local large language models by simply using them!

15

112

517

AndriyMulyar

@andriy_mulyar

1 year

Huge update on open source LLMz 💥 The Falcon model is now completely open source. Previously it was released under a license that required commercial royalty payments.

17

93

499

AndriyMulyar

@andriy_mulyar

1 month

How do models like GPT-4o and Meta’s Chameleon generate images? Answer: They don’t, they generate tokens. A short thread on multimodal tokenizers:

10

52

486

AndriyMulyar

@andriy_mulyar

1 year

Huge upgrade for LLMs💥 You don't need to fine-tune! Augment your LLMs with memory with a powerful open source vector database.

GitHub - nmslib/hnswlib: Header-only C++/python library for fast approximate nearest neighbors

Header-only C++/python library for fast approximate nearest neighbors - nmslib/hnswlib

github.com

13

88

468

AndriyMulyar

@andriy_mulyar

1 year

local llms nearly have apple silicone support with @ggerganov latest ggml version  gpt4all will soon support 40 tok/s inference of 7B transformer decoders on a Mac! open source the data open source the models gpt4all

13

65

465

AndriyMulyar

@andriy_mulyar

1 year

Have you heard of Deepscatter? 🗺️ Deepscatter is the only graphics engine that supports the rendering of billions of points in your web browser. It is non-commercially open source and built by Nomic's resident WebGL wizard @benmschmidt .

7

85

454

AndriyMulyar

@andriy_mulyar

1 year

Google used Atlas to visualize its LLM embeddings 🗺️ - Find out what you can learn by interactively exploring 8M embeddings.

7

79

434

AndriyMulyar

@andriy_mulyar

1 year

Interactively Explore 21M Scientific Articles on One Screen 🗺️

9

94

436

AndriyMulyar

@andriy_mulyar

1 year

Local LLMs work out of the box with @LangChainAI 🦜! Run chat in server mode and get started! Instructions:

7

85

394

AndriyMulyar

@andriy_mulyar

1 year

tell me you became an AI expert in November 2022 without telling me you became an AI expert in November 2022

Itamar Golan 🤓

@ItakGol

1 year

1/ Holy Moses 🤯 Is Vector Databases (Pinecone, Chroma...) soon to be DEAD? 🤔 Anthropic just expanded their Claude LLM's context window to 100K tokens. X3 than GPT-4 not-yet-released 32K version. 🚀 Here is my full analysis ⤵️⤵️⤵️

26

42

169

21

15

380

AndriyMulyar

@andriy_mulyar

1 year

The power of clean data: gpt4all beats chatgpt on certain hallucination benchmarks. 🗺️

9

39

353

AndriyMulyar

@andriy_mulyar

1 year

Excited to announce that GPT4All is now an official Langchain backend! 💥 your own models. on your own hardware. gpt4all.

LangChain

@LangChainAI

1 year

Rather large 🦜🔗0.0.131 release! 🆓GPT4all model ( @nomic_ai ) 🦙Llama-cpp model ⏹️Support for @qdrant_engine local db 🌲Zilliz cloud ( @milvusio ) Vectorstore support 📧New OutlookMessage Document Loader 🕸️New Selenium Document Loader 🪟 Support for SQL views in SQLChain 🧵

12

84

589

12

38

346

AndriyMulyar

@andriy_mulyar

1 year

GPT4All on a Nintendo DS lite, DSi and 3DS New hardware? No problem.

14

56

333

AndriyMulyar

@andriy_mulyar

9 months

gpt4all pre-release with mistral 7b running locally is ⚡. 34 tok/s on Mac metal. open-source and ships with support for nearly every GPU (amd, intel, nvidia, etc) you can try the nightly dev-build on discord.

17

30

317

AndriyMulyar

@andriy_mulyar

1 year

To create a gpt4all, you need to pre-train on trillions of tokens. we have the tokens. we have the gpus. we need your help to curate the terabytes of text. consider joining @nomic_ai to make history and open-source a powerful foundation model.

7

47

302

AndriyMulyar

@andriy_mulyar

1 year

The elite team of GPT4All community hackers is working tirelessly to address this. A GPT4All must run natively on All devices and be accessible to All. Remember, the web browser is the world's best distribution platform for software. Exciting announcements to come.

Brian Roemmele

@BrianRoemmele

1 year

@frhd27 Thank you. I am working on a free how to. Most folks have no ability to do many of the things in this link. It would add to the confusion. But some can just click your link and have at it if they are so inclined.

6

7

175

9

28

291

AndriyMulyar

@andriy_mulyar

1 year

Can someone point me to a deployed 'AI agent' that is found useful by a *some* group of people outside of its developers.

32

8

287

AndriyMulyar

@andriy_mulyar

1 year

Then God said, "Let there be Typescript", and there was Typescript. Official GPT4All @typescript Bindings are out! The elite team of hackers moves fast. opensource the data. opensource the models. gpt4all.

GitHub - nomic-ai/gpt4all-ts: gpt4all and llama typescript bindings

gpt4all and llama typescript bindings. Contribute to nomic-ai/gpt4all-ts development by creating an account on GitHub.

github.com

5

52

279

AndriyMulyar

@andriy_mulyar

1 year

Big News for Open Source AI 🎉 I'm excited to announce that @nomic_ai is doubling down on its commitment to making AI systems more accessible and explainable with our latest 17m Series A led by @coatuemgmt .

Open-source AI model creator Nomic raises $17 million led by Coatue

AI startup Nomic has raised $17 million in a new funding round from investors led by Coatue, the companies told Reuters.

www.reuters.com

41

32

273

AndriyMulyar

@andriy_mulyar

1 year

You can spin up your own hosted GPT4All on @modal_labs in 10 lines of code!

3

59

265

AndriyMulyar

@andriy_mulyar

1 year

Embeddings uncover scientific fraud - Check out how looking at embeddings of your data allows you to uncover patterns like potential scientific fraud. This interactive visual is powered by @nomic_ai embedding platform and @benmschmidt graphics engine

10

34

258

AndriyMulyar

@andriy_mulyar

1 year

Tired of breaking llama.cpp changes? 🔨 GPT4All is working to support old and new versions of llama.cpp with dynamic submoduling of ggML. Your models will just work! Come help us build the most stable ecosystem for local LLMs!

6

32

242

AndriyMulyar

@andriy_mulyar

5 months

Announcing Nomic Embed 🧨 You can now train your own OpenAI quality text embedding model. - Open source, fully reproducible text embedding model that beats OpenAI and Jina on long context tasks. - 235M text pairs openly released for training 💰 - Apache 2 License

17

37

242

AndriyMulyar

@andriy_mulyar

1 year

GPT4All will support all ggML and llama.cpp versions going forward!💥 Try 100's of different CPU LLMs on @huggingface all from the same chat client and python package! Instructions: …

10

42

240

AndriyMulyar

@andriy_mulyar

1 year

GPT4All is the hub for open source LLMs according to leaked internal Google documents 💥

Google "We Have No Moat, And Neither Does OpenAI"

Leaked Internal Google Document Claims Open Source AI Will Outcompete Google and OpenAI

www.semianalysis.com

12

48

227

AndriyMulyar

@andriy_mulyar

1 year

@jonathanbesomi found it on a USB that fell off a truck 🚚

5

2

219

AndriyMulyar

@andriy_mulyar

1 year

PromptLayer now stands behind the GPT4All movement! 🍰 When you use the OpenAI API through @promptlayer , you now have an opt-in option to share all your request outputs with the GPT4All open source data lake.

6

34

211

AndriyMulyar

@andriy_mulyar

1 year

my Twitter feed is full of ph.d. students having an existential crisis

4

10

208

AndriyMulyar

@andriy_mulyar

1 year

Orca Mini at 40 tok/sec on Apple Metal in

9

34

193

AndriyMulyar

@andriy_mulyar

9 months

Large Language Models Now Run on All GPUs with GPT4All 🚀 GPT4All is the first software to support all modern @AMD , @intel , @Qualcomm , and @nvidia GPUs for running LLMs. You don't need to know how to code to use the tech revolutionizing the world.

Run LLMs on Any GPU: GPT4All Universal GPU Support

Nomic AI releases support for edge LLM inference on all AMD, Intel, Samsung, Qualcomm and Nvidia GPU's in GPT4All.

blog.nomic.ai

6

37

188

AndriyMulyar

@andriy_mulyar

1 year

High-quality pretraining sets like RedPajama are a key ingredient in democratizing access to LLMs. Here is a brief exploration of what an LLM trained on RedPajama would see during training👀 Explore in Atlas:

4

30

176

AndriyMulyar

@andriy_mulyar

9 months

@paul_rottger @MistralAI while I too like Twitter points, a good pretrained LLM will always be able to do this. If you want to complain about safety, you should be evaluating a finetuned/rlhf'd chat model and saying things. You can do this with a pre-trained LLaMa2 as well. Nothing new.

3

0

175

AndriyMulyar

@andriy_mulyar

1 year

One line code change to use any GPT4All model from your LLM apps! Just point to localhost! You can even use them through the official OpenAI Python API! The Elite GPT4All Hackers have struck again.

Nomic AI

@nomic_ai

1 year

Big New Release of GPT4All📶 You can now use local CPU-powered LLMs through a familiar API! Building with a local LLM is as easy as a 1 line code change! Simply spin up the chat app at and place it in server mode! Documentation:

19

146

607

5

30

174

AndriyMulyar

@andriy_mulyar

1 year

You wouldn't let your student grade their own exam right? I would question the scientific integrity of any senior author on a paper who let 'lets just eval using GPT4!' slide through the early draft discussions of a paper. This is just silly.

Exploring the MIT Mathematics and EECS Curriculum Using Large...

We curate a comprehensive dataset of 4,550 questions and solutions from problem sets, midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and Computer Science...

arxiv.org

15

8

170

AndriyMulyar

@andriy_mulyar

1 year

You can get a sense of the data diversity in this interactive viewer: code, stories, questions

6

18

166

AndriyMulyar

@andriy_mulyar

1 year

We improve on GPT4All by: - increasing the number of clean training data points - removing the GPL-licensed LLaMa from the stack - Releasing easy installers for OSX/Windows/Ubuntu Details in the technical report:

11

14

161

AndriyMulyar

@andriy_mulyar

1 year

Embed4All Generate embedding *without* an API key.

Nomic AI

@nomic_ai

1 year

GPT4All now supports Text Embeddings ⚡ - Generate text embeddings of arbitrary length documents for free on CPU at 8,000 tok/second. - No external dependencies except C.

23

145

671

8

26

151

AndriyMulyar

@andriy_mulyar

1 year

A GPT4All runs all devices. WebGPU enables the distribution of on edge large language models to millions of individuals and tens of thousands of enterprises. The future is bright.

Ben Schmidt / @[email protected]

@benmschmidt

1 year

Big day for the Web: Chrome just shipped WebGPU without flags. Someone on @nomic_ai 's GPT4All discord asked me to ELI5 what this means, so I'm going to cross-post it here—it's more important than you'd think for both visualization and ML people. (thread)

15

214

943

2

23

141

AndriyMulyar

@andriy_mulyar

1 year

Local LLMs now have plugins! Privately chat with your data with GPT4All. Open source and free to use!

Nomic AI

@nomic_ai

1 year

Local LLMs now have plugins! 💥 GPT4All LocalDocs allows you chat with your private data! - Drag and drop files into a directory that GPT4All will query for context when answering questions. - Supports 40+ filetypes - Cites sources.

43

181

817

4

23

136

AndriyMulyar

@andriy_mulyar

1 year

Large Language Model Powered Video Games Are Now Feasible With GPT4All🎮🕹️ Join the discord and build the future with us: (credit: #teddybear082 on GPT4All Discord)

3

29

124

AndriyMulyar

@andriy_mulyar

1 year

apache-2'ing LLaMa weights would probably save a few millions tons of CO2 over the next 6 months. GPUs go brrrrrrr. how's that for a carbon offset. @ylecun

5

11

128

AndriyMulyar

@andriy_mulyar

1 year

GPT4All LocalDocs Plugin 🔌 - Lets businesses privately chat with their employee handbooks and cites sources! - Sideloaded Samantha model ( @erhartford ) specialized for assistant interaction! - Accelerated by new GPT4All Apple Silicon support ⚡ Try it at

4

20

115

AndriyMulyar

@andriy_mulyar

7 months

who is the anthropic customer that said '100k token context isn't enough for us' and who is the pm that agreed to prioritize it lol

16

5

117

AndriyMulyar

@andriy_mulyar

1 year

GPT4All-J is packaged in an easy-to-use installer. You are a few clicks away from a locally running large language model that can - answer questions about the world - write poems and stories - draft emails and copy all without the need for internet access.

9

6

111

AndriyMulyar

@andriy_mulyar

6 months

AI is nothing without open source #keepAIopen

7

9

108

AndriyMulyar

@andriy_mulyar

1 year

Early Access Announcement 🚪 Early access to the newest GPT4All model is available through a discord bot (running on CPU and built by an elite open source community hacker). Try it out from any device.

5

21

108

AndriyMulyar

@andriy_mulyar

1 year

a vector db is now the 'calculator app' of learning to code (:

will depue

@willdepue

1 year

tinyvector - the tiny, least-dumb, speedy vector embedding database. pretty much: you don't need complicated algos, just brute force nearest neighbors. pre-launching this project + why i'm building this:

22

54

748

4

7

106

AndriyMulyar

@andriy_mulyar

1 year

The elite hackers are shipping GPT4All updates every few days. Models are improving quickly.

Brian Roemmele

@BrianRoemmele

1 year

The moral dilemma. GPT4All-(jazzy) vs ChatGPT-3.5. Sometimes the simple answer is the best answer.

37

11

172

2

8

104

AndriyMulyar

@andriy_mulyar

1 year

pretty sweet feedback from folks who have taken it for a spin!

7

3

104

AndriyMulyar

@andriy_mulyar

1 year

The GPT4All movement grows by the day. Our community is 10k people strong and filled with elite open-source hackers paving the way to a decentralized future. We will open-source the data. We will open-source the models. #GPT4All Join the movement:

Join the Nomic AI Discord Server!

The official discord server for Nomic AI! Hang out, Discuss and ask question about Nomic Atlas or GPT4All | 31051 members

discord.com

3

10

102

AndriyMulyar

@andriy_mulyar

4 months

Nomic Embed v1.5 is out 🪆🪆🪆 - Variable-sized embeddings with matryoshka learning and an 8192 context. - Outperforms OpenAI text-embedding-3-small across output sizes. - Open source, open training code, open data. How does Matryoshka Learning work?

5

13

95

AndriyMulyar

@andriy_mulyar

11 months

I guess we can just ignore the fact that running llama and llama2 at interactive rates (this is slow) with pure C has been possible for three months in and use this instead

Andrej Karpathy

@karpathy

11 months

If we can get 7B model to run at nice and interactive rates then we can go from "scratch-trained micromodels" to "LoRA finetuned 7B base model", all within the code of the minimal llama2.c repo (both training and inference). Can reach more capability and with less training data.

16

30

501

5

8

90

AndriyMulyar

@andriy_mulyar

8 months

Discover the latest AI research published to ICLR 2024 By @yihengxu_

ICLR 2024 Submission | Atlas

Structure unstructured datasets of text, images, embeddings, audio and video.

atlas.nomic.ai

3

11

92

AndriyMulyar

@andriy_mulyar

6 months

@willdepue @yacineMTB that is not a valid float32 value

4

0

89

AndriyMulyar

@andriy_mulyar

3 months

wtf, Amazon Go wasn't AI powered and literally just outsourced video monitoring of picked up items to India I never want to be told 'it doesn't scale' again

Amazon Ditches 'Just Walk Out' Checkouts at Its Grocery Stores

Amazon Fresh is moving away from a feature of its grocery stores where customers could skip checkout altogether.

gizmodo.com

7

16

89

AndriyMulyar

@andriy_mulyar

1 year

Training this thing wasn't a cakewalk as @zach_nussbaum can attest. Learn about Zach's weekend tribulations at:

8

7

87

AndriyMulyar

@andriy_mulyar

1 year

Some samples (out of training set) Valid Python generation with markdown

4

89

AndriyMulyar

@andriy_mulyar

1 year

gpt4all

Jaya Gupta

@JayaGup10

1 year

💀

13

90

5

12

84

AndriyMulyar

@andriy_mulyar

11 months

Starcoder 3B runs on CPU ⚡ Excited to launch @huggingface 's Starcoder model in on CPU! Local code models will be everywhere

BigCode

@BigCodeProject

11 months

@nomic_ai team already added support for StarCoderBase-3B in their GPT4ALL local models. Download the model at: & follow the docs: Stay tuned for the 7B model integration!

3

8

34

3

16

84

AndriyMulyar

@andriy_mulyar

1 year

You will own your AI.

Brian Roemmele

@BrianRoemmele

1 year

You will own your own AI. Final testing on a new massively smaller 100% locally running ChatGPT 3.5 turbo type of LLM AI in your hard drive on any 2015+ laptop. I will have pre-configured downloads and it is massively smaller than most models I have, just 4gb. Out soon!

336

2K

13K

4

3

84

AndriyMulyar

@andriy_mulyar

1 year

I suppose I forgot to mention that this model runs on your CPU with 4 GBs of RAM at 10 words (tokens) per second.

8

4

83

AndriyMulyar

@andriy_mulyar

6 months

9 months ago @nomic_ai had a hack weekend where we trained an LLM to mimic ChatGPT. It worked better than expected and we decided to call it gpt4all the morning of the codebase release. The rest was history. Happy New Year. To a 2024 filled with open source, models and data.

7

8

83

AndriyMulyar

@andriy_mulyar

1 year

AI winter confirmed

469

@cephaloform

1 year

if i see one more github star graph with the caption "probably nothing" im quitting ai and moving onto creating doilies

3

0

24

4

5

77

AndriyMulyar

@andriy_mulyar

1 year

Local LLMs have hit .NET! You can now use local LLMs on CPU in C#!

C# bindings by mvenditto · Pull Request #650 · nomic-ai/gpt4all

Describe your changes First working version of the C# binding. Issue ticket number and link #649 Notes Tested the build on Windows and Linux(Ubuntu). OSX support can be easily added but I do not ...

github.com

6

7

81

AndriyMulyar

@andriy_mulyar

1 year

Alongside installers, we release the training data, model weights and perform extensive evaluations of comparable models:

3

81

AndriyMulyar

@andriy_mulyar

8 months

Local LLMs have improved significantly since last March. Models like Mistral 7B are often drop-in replacements for common queries to the giants (GPT4). Give them a shot if you had a poor experience on your first try!

Nomic AI

@nomic_ai

8 months

Monthly reminder for everyone affected by today's @OpenAI outage: Local #GPT4All models like @MistralAI 7B run at 20tokens/sec+ on a Macbook air and don't go down.

10

34

301

6

10

81

AndriyMulyar

@andriy_mulyar

1 year

local models never go down #gpt4all

5

10

80

AndriyMulyar

@andriy_mulyar

1 year

i was today years old when i learned people are unplugging their routers to verify that gpt4all isn't accessing an external api

5

4

79

AndriyMulyar

@andriy_mulyar

1 year

the first large language model running on a Nintendo DS. open the data. open the models. gpt4all. credit: Tuxifan #0981

video 2023 04 04 00 07 10

null

www.youtube.com

3

15

78

AndriyMulyar

@andriy_mulyar

1 year

OpenAI may start releasing some open source models! Seems like open-source is a bigger business risk than describing your data collection / training procedures

4

16

77

AndriyMulyar

@andriy_mulyar

3 months

GGUF security alert 🚨 A heap based buffer overflow vulnerability exists in GGUF files that can be triggered by a malicious file. gpt4all is working to address and mitigate risks for all users. Exercise caution when running recent GGUF files from unknown origins.

4

16

75

AndriyMulyar

@andriy_mulyar

8 months

@ChombaBupe lol idk if they are speechless. this type of adversarial data perturbation is nearly a decade old

3

1

72

AndriyMulyar

@andriy_mulyar

1 year

This dataset is 16x larger than Alpaca!

3

1

71

AndriyMulyar

@andriy_mulyar

1 year

Exciting new release! PromptLayer 🍰 is an early backer of the GPT4All movement! They have native opt-in integrations to the GPT4All data lake (try it!). If you care about data provenance and privacy for your LLM-powered apps, look no further than PromptLayer!

PromptLayer

@promptlayer

1 year

🪩 New Analytics Page 🪩 Now you can track and visualize: 1. Cost 💰 2. Latency 🏎️ 3. Model Usage 🤖 4. Prompts 📃 Great for teams, we all know that one person who will live on this page! 🍰🍰🍰🍰

1

3

37

3

12

70

AndriyMulyar

@andriy_mulyar

1 year

For everyone interested in where to take your NLP research directions, Open AI suggests that you should just study their LLM and hope to work for them. They even made it cheap for you to study it!

Jason Wei

@_jasonwei

1 year

I’m hearing chatter of PhD students not knowing what to work on. My take: as LLMs are deployed IRL, the importance of studying how to use them will increase. Some good directions IMO (no training): 1. prompting 2. evals 3. LM interfaces 4. safety 5. understanding LMs 6. emergence

52

285

2K

1

6

70

AndriyMulyar

@andriy_mulyar

1 year

i'll be dreaming about dropping flash drives with a certain 4gb file across the borders of authoritarian regimes. goodnight.

4

2

67

AndriyMulyar

@andriy_mulyar

1 year

You can explore the final curated training set in Atlas You'll find large regions dedicated to creative prompts like stories and poems in addition to an increased number of multi-turn responses.

3

7

68

AndriyMulyar

@andriy_mulyar

1 year

visualize your model logits during training with 10 lines of code! if you use pytorch @LightningAI i would love someone to take my latest callback for a spin. dm feedback!

1

12

68

AndriyMulyar

@andriy_mulyar

3 months

a searchable data map of the GPTs people make on the @OpenAI platform

OpenAI Custom GPT Data Map | Atlas

https://github.com/beetrove/openai-gpts-data/blob/main/GPTs_5_percent_random_sample.xlsx

atlas.nomic.ai

3

13

65

AndriyMulyar

@andriy_mulyar

1 year

The GPT4All Open Source data lake stores all ingested data in a constantly visible state, allowing anyone to download it. Improved GPT4All models are training on early versions of the data lake as we tweet. open source the data. open source the models. gpt4all.

2

10

64

AndriyMulyar

@andriy_mulyar

1 year

A GPT4All does not support or subvert specific political ideologies or choose winners. open source the data open source the models #gpt4all .

China releases new AI rules as tech giant Alibaba unveils ChatGPT rival

Alibaba working on ChatGPT rival Tongyi Qianwen, which it plans to integrate across its services

www.yahoo.com

3

5

61

AndriyMulyar

@andriy_mulyar

5 months

GPT4All - v2.6.2 - has just been released! * Update to latest llama.cpp * Update to newly merged vulkan backend * Partial GPU offloading support * New localdocs speed increases and features * New GUI settings option for configuring how many layers to put on GPU * New lightmode

3

10

61

AndriyMulyar

@andriy_mulyar

2 months

Run LLaMA 3 on edge devices with open source GPT4All ⚡⚡ - The best open weights 8B LLM in the world - Runs at 25 tok/s on Mac Metal

1

6

61