Mishig Davaadorj @mishig25 Twitter profile

Last Seen Profiles

@TammyLovin_

@bokeplokalmalam

@PenaEPereira

@jloudboys

@r0_i9l

@KiandreTerry_

@enhance_exp

@oppasanta

@danbdesign

@hackebrot

@gjun0501

@yaeumiko

@scottycknight

@AJGuglielmi

@Bully2Info

@JeffreyMcMenemy

@jackieAsullivan

@JhonnyCabreraCR

@sumisoeup

@its_ayaaaa2

@ANMOLSI83027486

@Q3Pg41685jdti7

@Gpjdwjagtm

@Roddy_94

@Medusa0796

@zdamen_

@Go_Jover

@stw_pdg

@MESpersaPobla

@sub05575636

@ZacKenton1

@Utd_chi

@s04_jp

@Swathi_dhana_

@ViitorRe

Mishig Davaadorj

@mishig25

2 years

16

205

2K

Mishig Davaadorj

@mishig25

2 years

You watch @netflix ; I watch @karpathy We are not the same

57

79

2K

Mishig Davaadorj

@mishig25

2 years

How do you draw an owl: 1. draw some circles 2. click "Diffuse the rest" We have made the greatest thing since MS Paint (using #stablediffusion ): Looking forward to seeing what you'll generate with it 😊

54

266

2K

Mishig Davaadorj

@mishig25

2 years

As exact as it gets

🪻bosco🪻

@selentelechia

2 years

what the fuck is "attention," exactly

134

17

382

20

106

1K

Mishig Davaadorj

@mishig25

2 years

text-to-3D text -> 2D image -> 3D point cloud Step 1: describe what you want -> Step 2: img generation with a diffusion model -> Step 3: 3D point cloud generation using a second diffusion model using the img from step 2 gr.demo:

12

235

1K

Mishig Davaadorj

@mishig25

2 years

Microsoft upgraded its search. Google upgraded its search. Github upgraded its search. Now, it is our turn. Let us begin:

10

91

771

Mishig Davaadorj

@mishig25

1 year

ML runs everywhere now because of 2 recent trends: * 𝚓𝚊𝚟𝚊𝚜𝚌𝚛𝚒𝚙𝚝-𝚏𝚒𝚌𝚊𝚝𝚒𝚘𝚗 of ML (transformers.js, huggingface.js) for running on browsers * 𝚌𝚙𝚙-𝚏𝚒𝚌𝚊𝚝𝚒𝚘𝚗 of ML (llama.cpp, bloomz.cpp, whisper.cpp) for running on embedded devices

12

61

570

Mishig Davaadorj

@mishig25

2 years

As the field of ML-for-3D grows, we've added 3D model viewer for 🤗Hub datasets For example, checkout this Cybertruck from @allen_ai 𝗢𝗯𝗷𝗮𝘃𝗲𝗿𝘀𝗲 dataset:

6

80

513

Mishig Davaadorj

@mishig25

2 years

text-to-image-editing words -> mask -> replacement describe what you want -> automatic mask generation with CLIPSeg -> replace mask with Stable Diffusion generation gr.demo:

9

108

493

Mishig Davaadorj

@mishig25

1 year

Pose 3D mode & render with Stable Diffusion (ControlNet) (forget about ray-tracing, path-tracing, or any kind of tracing in that respect #FutureIsNow ) try gr.demo:

4

116

495

Mishig Davaadorj

@mishig25

2 years

Not sure if RLHF is the future, but it is definitely the present. As such, you can find RLHF datasets on the Hub 1. @OpenAI / WebGPT Comparisons

6

80

497

Mishig Davaadorj

@mishig25

3 years

Play with the new image segmentation widget on 🤗Hub 🎉

2

56

325

Mishig Davaadorj

@mishig25

2 years

Excited about how LLMs (such as Galactica) will enhance scientific writing @Gradio demos now support 𝐋𝐚𝐓𝐞𝐗

5

30

287

Mishig Davaadorj

@mishig25

2 years

ICON by @yuliangxiu et al. is very impressive! Moreover, you can try right away thanks to @Gradio 3D capabilities

4

35

264

Mishig Davaadorj

@mishig25

1 year

There are wrappers that are built on top of open-source LLMs to generate syntactically valid json, yaml, or context-free grammar langs, its kinda big deal. is Gradio demo of Jsonformer project that lets you generate syntactically valid json 🧵

7

43

259

Mishig Davaadorj

@mishig25

2 years

Did you know that the most used language in ML pull-requests is NOT python 🐍 but... emojis? We know that as well, so we've added support for reactions in @huggingface PRs /Discussions! You can now use 👍 🤝 😔 🤯 🤗 ❤️ Any other favorite emoji we should add?

8

25

251

Mishig Davaadorj

@mishig25

5 months

At @huggingface , we are adding more support to GGUF (model format by @ggerganov ). The number of GGUF models on the hub has been exploding & doesn't look like it is gonna slow down🔥 see more at:

9

37

257

Mishig Davaadorj

@mishig25

4 months

We've just published diffusion course by @johnowhitaker @_lewtun et al. at It is a great resource to learn the basics of diffusion models & @diffuserslib

1

42

235

Mishig Davaadorj

@mishig25

2 years

tired: image generations wired: image inpainting this is literally the coolest demo since the beginning of time

5

21

235

Mishig Davaadorj

@mishig25

2 years

You can now embed any 🤗Space into your website or blog

6

26

226

Mishig Davaadorj

@mishig25

8 months

Spending my holidays trying to catch up on all the interesting models on 🤗Hub

3

34

213

Mishig Davaadorj

@mishig25

2 years

14 million text-to-image prompt dataset with their hyperparameters (DiffusionDB dataset from @polodataclub ) Quite useful for both research & product at the same time

2

46

212

Mishig Davaadorj

@mishig25

6 years

I created a browser based environment where humanoids are trained to walk through NeuroEvolution of Augmenting Topologies (NEAT) @kenneth0stanley | Tools used: @TensorFlow , Neataptic.js, Planck.js (a Box2D rewrite)

3

56

188

Mishig Davaadorj

@mishig25

3 years

1/ Creating smart NPC (non-player character) is as easy as just calling @huggingface Inference API #gamedev #NLP I've created this WebGL demo using 🤗 + @playcanvas Code and demo are available at 🤗 Spaces

4

40

184

Mishig Davaadorj

@mishig25

1 year

text-to-3d is in @diffuserslib through openai/shap-e checkpoints !

2

41

187

Mishig Davaadorj

@mishig25

2 years

Transformers work on different modalities (from text to vision to audio) because everything is a "sequence of tokens" 🧵 Thread on how any data type can be viewed as a "sequence of tokens" 1/

5

21

181

Mishig Davaadorj

@mishig25

2 years

You can now visualize reinforcement learning agents directly on the @huggingface Hub 🤗 with our new video widget 🪄

4

41

170

Mishig Davaadorj

@mishig25

2 years

Create a "not-so-bad" computer vision app using 🤗 API Accelerated Inference Thread 🧵 1/

1

26

171

Mishig Davaadorj

@mishig25

1 year

some big models in the works & be released soon @huggingface

5

12

167

Mishig Davaadorj

@mishig25

1 year

Yall asked for that 6 month pause (we listen to our users)

StutterBuddyAi

@StutterBuddy

1 year

Huggingface down, what to do with life

1

10

6

8

156

Mishig Davaadorj

@mishig25

2 years

ᴇᴅɪᴛ ɪᴍaɢeꜱ ᴡɪᴛʜ ᴡᴏʀᴅꜱ 🤗Diffusers now supports InstructPix2Pix #stablediffusion model by Tim Brooks, Aleksander Holynski, et al. Read more on how to use it with diffusers: #MichelangeloTheGreatest

3

21

129

Mishig Davaadorj

@mishig25

1 year

If you want to use Code Llama in VS Code, we got you

4

23

129

Mishig Davaadorj

@mishig25

1 year

Imagine Apple VisionPros running Fast Segment Anything

3

26

124

Mishig Davaadorj

@mishig25

1 year

How we combined @threejs with ControlNet-v1.1 𝚝𝚑𝚛𝚎𝚎.𝚓𝚜 -> 𝚘𝚗𝚎 𝚘𝚏 𝙲𝚘𝚗𝚝𝚛𝚘𝚕𝙽𝚎𝚝 𝚒𝚗𝚙𝚞𝚝 𝚝𝚢𝚙𝚎𝚜 (𝚒𝚗 𝚝𝚑𝚒𝚜 𝚌𝚊𝚜𝚎, 𝚌𝚊𝚗𝚗𝚢 𝚎𝚍𝚐𝚎 𝚍𝚎𝚝𝚎𝚌𝚝𝚒𝚘𝚗) -> 𝙲𝚘𝚗𝚝𝚛𝚘𝚕𝙽𝚎𝚝 demo:

2

28

119

Mishig Davaadorj

@mishig25

2 years

“When AI critics get together, they talk about sentience and consciousness and emergence. When AI scientists/engineers get together, they talk about where you can get cheap GPU” - Pablo Picasso 2023

Norgard

@BrianNorgard

2 years

“When art critics get together, they talk about form and structure and meaning. When artists get together, they talk about where you can buy cheap turpentine oil.” —Pablo Picasso

7

56

539

3

21

117

Mishig Davaadorj

@mishig25

2 years

As transformers generalized from NLP to other modalities, so did 🤗Hub On 🤗Hub, you can find checkpoints in CV, audio, RL, & even table-question-answering. Moreover, you can even play 🕹️with them:

Andrej Karpathy

@karpathy

3 years

The ongoing consolidation in AI is incredible. Thread: ➡️ When I started ~decade ago vision, speech, natural language, reinforcement learning, etc. were completely separate; You couldn't read papers across areas - the approaches were completely different, often not even ML based.

414

2K

8K

1

17

110

Mishig Davaadorj

@mishig25

2 years

Every model on @huggingface now has "table of contents" 🏛️ for easier navigation Model Cards rock 🔥

1

10

110

Mishig Davaadorj

@mishig25

1 year

𝗥𝗟𝗛𝗙 tag on 🤗Blog to find all the Reinforcement Learning from Human Feedback posts:

1

28

108

Mishig Davaadorj

@mishig25

2 years

Tired of cliché dystopian depiction of AGI in Hollywood, so we decided to make a film about AGI & awesomeness

8

9

106

Mishig Davaadorj

@mishig25

5 months

Now, you can quickly inspect GGUF files on the Hub. See their metadata & tensors info directly from model pages

3

19

107

Mishig Davaadorj

@mishig25

3 years

You can now upload models, datasets, and spaces directly through the @huggingface hub interface so let me try with a small model I had locally 😊😊😊

1

22

105

Mishig Davaadorj

@mishig25

2 years

Hub supports now webhooks, which means your app can update/react realtime as model, space, or dataset changes 🔄 Read more in the docs:

2

14

102

Mishig Davaadorj

@mishig25

1 year

𝚑𝚞𝚐𝚐𝚒𝚗𝚐𝚏𝚊𝚌𝚎.𝚓𝚜 is literally the biggest thing to happen to 𝘔𝘓 𝘹 𝘑𝘚 since 𝚃𝚎𝚗𝚜𝚘𝚛𝙵𝚕𝚘𝚠.𝚓𝚜

GitHub - huggingface/huggingface.js: Utilities to use the Hugging Face Hub API

Utilities to use the Hugging Face Hub API. Contribute to huggingface/huggingface.js development by creating an account on GitHub.

github.com

8

13

99

Mishig Davaadorj

@mishig25

2 years

text-to-emoji generate endless amount of emojis & app icons gr.demo:

2

23

100

Mishig Davaadorj

@mishig25

6 months

Sipping my whiskey from @groupe_lactalis bottle. Testing YOLOv9 that is running entirely in the browser

5

13

97

Mishig Davaadorj

@mishig25

1 year

If you don't wanna spend rest of your life stackoverflowing apis of different langs & libraries, try with Code Llama 35B Instruct version

0

17

91

Mishig Davaadorj

@mishig25

3 months

Path to open source humanoids. Let's go 🔥 LeRobot - state-of-the-art ml for real-world robotics

5

14

89

Mishig Davaadorj

@mishig25

3 years

@huggingface Hub🤗 has now Object Detection widget 🎉 Check out DETR for instance

0

16

88

Mishig Davaadorj

@mishig25

3 years

One of the perks of working from @huggingface Paris office 🇫🇷 is that you can watch Messi, Neymar, Mbappe, De Bryune, Mahrez, Grealish play in the same match ⚽️⚽️⚽️

5

3

85

Mishig Davaadorj

@mishig25

2 years

context aware image transformation using @diffuserslib v0.10.0 (utilizing Depth2Image model) example: transforming the initial image into "a photo of a bag of gummy bears on a basketball court" gr.demo:

2

19

84

Mishig Davaadorj

@mishig25

2 years

How do language models (like BERT or GPT) "see" words? TLDR: whereas we see 𝚆𝚎̄𝚕𝚌𝚘́𝚖𝚎̂ 𝚝𝚘́ 𝚝𝚑𝚎̈ 🤗 𝚃𝚘̂𝚔𝚎́𝚗𝚒̄𝚣𝚎̄𝚛𝚜, language models see [𝟷0𝟷, 𝟼𝟷𝟼0, 𝟸000, 𝟷𝟿𝟿𝟼, 𝟷00, 𝟷𝟿𝟸0𝟺, 𝟷𝟽𝟼𝟸𝟿, 𝟸0𝟷𝟻, 𝟷0𝟸] 🧵 on Tokenization by examples 1/

2

9

78

Mishig Davaadorj

@mishig25

1 year

LLaMA weights:

3

17

77

Mishig Davaadorj

@mishig25

1 year

RefinedWeb is a massive English web dataset on which falcon-40b was pretrained on. Atm, falcon-40b holds the first position on top of llama-65b on Open LLM Leaderboard. Explore the dataset through datasets-viewer:

1

13

73

Mishig Davaadorj

@mishig25

2 years

🤗 Hub & Transformers now support ᴢᴇʀᴏ-ꜱʜᴏᴛ ɪᴍᴀɢᴇ ᴄʟᴀꜱꜱɪꜰɪᴄᴀᴛɪᴏɴ In this example, I'm using ʟᴀɪᴏɴ/ᴄʟɪᴘ-ᴠɪᴛ-ʟ-14-ʟᴀɪᴏɴ2ʙ-ꜱ32ʙ-ʙ82ᴋ, which is "the best performing open-source ViT CLIP model released" (more info below)

1

14

69

Mishig Davaadorj

@mishig25

3 years

Really excited to join @huggingface (has been a fan of 🤗, open source software, & open science for a long time). The French Tech Visa rocks! 🇫🇷

Julien Chaumond

@julien_c

3 years

We just helped a team member from Mongolia get a work visa to France. June 10: offer sent to candidate(&accepted) June 16: appointment at the FR consulate in Ulaanbaatar, Mongolia 🇲🇳 June 22: visa application approved June 30: @mishig25 will travel to France 🎉 Go France!! 🇫🇷🇫🇷

13

46

397

3

11

68

Mishig Davaadorj

@mishig25

1 year

Testing llama-2-70B code capabilities on Should we work on code interpreter for 🤔?

2

10

61

Mishig Davaadorj

@mishig25

2 years

🧵on how we implemented Under the hood, we are using @meilisearch . Decided to use it after finding its performance & feature-set to be quite impressive. I don't wanna be that guy: but did I mention that meiliseach is written in Rust 🦀 & OSS. 1/N

Full Text Search - Hugging Face

huggingface.co

Mishig Davaadorj

@mishig25

2 years

Microsoft upgraded its search. Google upgraded its search. Github upgraded its search. Now, it is our turn. Let us begin:

10

91

771

1

14

64

Mishig Davaadorj

@mishig25

1 year

Curated daily papers by the one @_akhaliq

1

17

59

Mishig Davaadorj

@mishig25

2 years

PRs & Discussions @huggingface now support video uploading/viewing 🎥 We are super excited to add this feature since videos (screencasts) are usually a great aid to any discussion 😊

1

9

59

Mishig Davaadorj

@mishig25

5 months

Today's trending models are: @CohereForAI @xai @GoogleAI @NousResearch @ByteDanceOSS

2

12

59

Mishig Davaadorj

@mishig25

2 years

Tweet inspired by:

Dave9000

@Dave_9000ish

2 years

Witness. The death of a meme

8

84

484

2

1

54

Mishig Davaadorj

@mishig25

1 year

@karpathy @osanseviero @karpathy you can use the webui to upload your model.bin file & use the download link afterwards as demonstrated in the video. Looking forward to your first repo on 🤗 Hub

1

5

56

Mishig Davaadorj

@mishig25

2 years

image-variations checkout this amazing 🤗Space by @Buntworthy @LambdaAPI : Find below more details, including how to use it with @diffuserslib

1

14

55

Mishig Davaadorj

@mishig25

4 months

Adding more GGUF support on hf-hub. Easy navigation between shards

4

13

53

Mishig Davaadorj

@mishig25

2 years

HF Spaces now support Docker read more:

1

9

53

Mishig Davaadorj

@mishig25

2 years

Friendly reminder that AK is a human, not a bot 🤖

AK

@_akhaliq

2 years

Had wisdom tooth extraction today so will probably be off during arxiv paper time 🦷

9

0

81

3

1

51

Mishig Davaadorj

@mishig25

1 year

TinyStories checkpoints and datasets available at by @EldanRonen

Andrej Karpathy

@karpathy

1 year

"Textbooks Are All You Need" is making rounds: reminding me of my earlier tweet :). TinyStories is also an inspiring read: We'll probably see a lot more creative "scaling down" work: prioritizing data quality and diversity over

28

185

1K

1

10

51

Mishig Davaadorj

@mishig25

2 years

@_akhaliq is a critical infrastructure

Jeremy Howard

@jeremyphoward

2 years

Sharing my secrets on

5

16

220

1

49

Mishig Davaadorj

@mishig25

1 year

video🎥 X AI🤖 ControlNet gets applied to video 🤯 gr.demo by @fffiloni :

0

9

45

Mishig Davaadorj

@mishig25

1 year

GANs are back. So are RNNs (with RWKV) Here is a friendly discussion between the two legendary creators (Schmidhuber & Goodfellow) at neurips 2016:

Ian Goodfellow: Generative Adversarial Networks (NIPS 2016 tutorial)

Generative adversarial networks (GANs) are a recently introduced class of generative models, designed to produce realistic samples. This tutorial is intended...

www.youtube.com

hardmaru

@hardmaru

1 year

GANs are back!

10

43

288

2

5

45

Mishig Davaadorj

@mishig25

6 months

Qualcomm entering the arena @Qualcomm

clem 🤗

@ClementDelangue

6 months

Terribly excited about open-source + on-device AI these days! Great to see @Qualcomm release 80+ models optimized and curated for their devices and chips on @huggingface :

5

77

495

2

7

44

Mishig Davaadorj

@mishig25

2 years

Visual Question Answering widgets are live on the 🤗Hub! In this example, the correct answer would have been "chilling", but ViLT🖼️📝answers are pretty close

2

8

43

Mishig Davaadorj

@mishig25

1 year

tldr: gpt-j (6B) finteuned on alpaca dataset @mrm8488 also did a similar thing where he finteuned bloom (7B) on alpaca dataset

Ali Ghodsi

@alighodsi

1 year

We are open sourcing Dolly, a ChatGPT-like model that can do instruction following, created for $30, trained 3 hours on 1 server. The secret in magical human-like interactivity probably lies in a small dataset.

40

468

2K

3

5

43

Mishig Davaadorj

@mishig25

3 years

@julien_c @LaFrenchTechEN @LaFrenchTech @France_Mongolie @francediplo @huggingface It was so fast that I didn't even had a chance to finish 🇫🇷 basics on @duolingo

1

44

Mishig Davaadorj

@mishig25

2 years

More libs 🏛️ => More docs 📖

1

6

42

Mishig Davaadorj

@mishig25

5 months

It is like one of those real-time diffusion demos but for text

gabriel

@gabrielchua_

6 months

Catch me if you can! 🐰 @GroqInc just added support for Gemma 7B. 🔥 Did up this simple @Gradio app to show how fast inference is, and imagine how smooth a LLM-powered autocomplete would feel with this.

13

38

205

3

42

Mishig Davaadorj

@mishig25

1 year

Pick your poison: 1. 𝘛𝘦𝘮𝘱𝘰𝘳𝘢𝘳𝘪𝘭𝘺 𝘱𝘢𝘶𝘴𝘦 𝘵𝘳𝘢𝘪𝘯𝘪𝘯𝘨 𝘱𝘰𝘸𝘦𝘳𝘧𝘶𝘭 𝘮𝘰𝘥𝘦𝘭𝘴! 2. 𝘋𝘦𝘮𝘰𝘤𝘳𝘢𝘵𝘪𝘻𝘦 𝘈𝘐 𝘳𝘦𝘴𝘦𝘢𝘳𝘤𝘩 𝘣𝘺 𝘱𝘶𝘣𝘭𝘪𝘤𝘭𝘺 𝘧𝘶𝘯𝘥𝘦𝘥 𝘧𝘢𝘤𝘪𝘭𝘪𝘵𝘺 𝘵𝘰 𝘵𝘳𝘢𝘪𝘯 𝘰𝘱𝘦𝘯 𝘴𝘰𝘶𝘳𝘤𝘦 𝘧𝘰𝘶𝘯𝘥𝘢𝘵𝘪𝘰𝘯 𝘮𝘰𝘥𝘦𝘭𝘴

3

5

42

Mishig Davaadorj

@mishig25

11 months

Paris AI scene is 🔥 comme f right now Please do come by @huggingface OSS event on oct 5th partiful: password: osftw

4

7

41

Mishig Davaadorj

@mishig25

1 year

Got some H100s

2

8

40

Mishig Davaadorj

@mishig25

2 years

Hub has a new GUI editor for updating metadata easily in model/dataset-cards for instance, try:

4

5

40

Mishig Davaadorj

@mishig25

5 months

@Thom_Wolf here are all the links & papers mentioned in the talk:

A little guide to building Large Language Models in 2024 - a mishig Collection

huggingface.co

0

4

39

Mishig Davaadorj

@mishig25

2 years

Editing files on 🤗Hub has improved drastically: better autocompletion, better syntax highlighting, & better indentation #justbetter Model cards are automatically parsed into YAML & Markdown sections

2

8

38

Mishig Davaadorj

@mishig25

3 months

GGUF model pages now show more information: 𝙼𝚘𝚍𝚎𝚕 𝚜𝚒𝚣𝚎 & 𝙰𝚛𝚌𝚑𝚒𝚝𝚎𝚌𝚝𝚞𝚛𝚎. We will be shipping more & more GGUF support in the coming days 🚀

2

6

37

Mishig Davaadorj

@mishig25

10 months

@Thom_Wolf Created 🤗Collection

zephyr story - a mishig Collection

huggingface.co

0

5

34

Mishig Davaadorj

@mishig25

9 months

Obviously, my favourite cafe

3

2

37

Mishig Davaadorj

@mishig25

1 year

In January, this prediction looked improbable 🎲 As of today, it looks inevitable 🎯 (with alpaca @StanfordCRFM , GPT-NeoXT-Chat @togethercompute , ChatGLM @thukeg among others)

Julien Chaumond

@julien_c

2 years

Prediction: there'll be 10 open reproductions of ChatGPT in 6 months and if i understand correctly, models are quite smaller than LLMs so they might be significantly easier to deploy at scale (maybe even single-GPU)

60

87

903

3

9

36

Mishig Davaadorj

@mishig25

7 months

Tried their image bg-removal demo. Works great!

BRIA AI

@bria_ai_

7 months

📷 Introducing Open-Source Background Removal by @BriaAI 📷 Now live on @huggingface , RMBG v1.4 excels in separating foreground from background across diverse categories, surpassing current open models. See demo [] #BriaAI #OpenSource #AI @briaai

25

70

321

2

5

35

Mishig Davaadorj

@mishig25

1 year

Native MacOS app (in Swift) for running stable diffusion using @Apple Core ML framework. Might be interesting for privacy reasons (as the imgs are generated on-device). obvvv, it is open-source: by @pcuenq

0

6

35

Mishig Davaadorj

@mishig25

1 year

Installing nvidia-driver

3

4

35

Mishig Davaadorj

@mishig25

2 years

Mishig Davaadorj

@mishig25

2 years

“When AI critics get together, they talk about sentience and consciousness and emergence. When AI scientists/engineers get together, they talk about where you can get cheap GPU” - Pablo Picasso 2023

3

21

117

3

5

34

Mishig Davaadorj

@mishig25

1 year

Impressive from @BlinkDL_AI project ("RWKV is an RNN with GPT-level language modeling and zero-shot performance")

0

5

34

Mishig Davaadorj

@mishig25

5 months

Downloading some quantized ggufs from & testing them on Vision Pro M2 neural engine. So far, the latency is good I'd say. whisper, mobileSam, & some llms (2b & 7b) Believe you me on-device AI is going 🔥

1

2

34

Mishig Davaadorj

@mishig25

1 year

HF Miami office

2

0

33

Mishig Davaadorj

@mishig25

1 year

Updated 𝚍𝚒𝚏𝚏𝚞𝚜𝚎-𝚝𝚑𝚎-𝚛𝚎𝚜𝚝 demo with @diffuserslib ControlNet implementation Try the demo: (sketch directly or upload your sketch)

1

9

33

Mishig Davaadorj

@mishig25

1 year

Join the discussions

Paper page - HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace

huggingface.co

AK

@_akhaliq

1 year

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace abs:

17

235

1K

0

6

31

Mishig Davaadorj

@mishig25

1 year

Does AI QR codes actually work? Yes, they do

3

2

30

Mishig Davaadorj

@mishig25

11 months

We would like to feature your blogpost . Please comment your username under the thread 🤗 We promise not to put any paywall 😂

14

8

31

Mishig Davaadorj

@mishig25

3 months

Next event of Paris AI running club is happening on May 20th 17:00 with @julien_c & other members of @huggingface We invite anyone/everyone to join us 🤗

Mishig Davaadorj

@mishig25

4 months

Anyone wanna join the Paris AI running club? Comment below Here with @HugoLaurencon from Idefics team & bug dawg @misovalko from Llama 3 team