merve's banner
merve's profile picture

merve

@mervenoyann • 86,495 subscribers

(mer-veh) open-sourceress at @huggingface 🧙🏻‍♀️ DM me for any feedback about HF 🤗 https://t.co/MhrMkGTm7p

Shorts

RF-DETR just landed to Hugging Face transformers 🥵🔥 sota real-time detection & segmentation models by Roboflow 💜 > play with our real-time demo > fine-tune the models on your use case with our tutorials (takes a toaster's VRAM) > or just hand them to your agents 😄

RF-DETR just landed to Hugging Face transformers 🥵🔥 sota real-time detection & segmentation models by Roboflow 💜 > play with our real-time demo > fine-tune the models on your use case with our tutorials (takes a toaster's VRAM) > or just hand them to your agents 😄

56,363 views

this is the BEST vision language model I have ever tried! Aria is a new model by Rhymes.AI: a 25.3B multimodal model that can take image/video inputs 🤩 They release the model with Apache-2.0 license and fine-tuning scripts as well 👏 I tested it extensively, keep reading to learn more 🧶

this is the BEST vision language model I have ever tried! Aria is a new model by Rhymes.AI: a 25.3B multimodal model that can take image/video inputs 🤩 They release the model with Apache-2.0 license and fine-tuning scripts as well 👏 I tested it extensively, keep reading to learn more 🧶

176,047 views

Real-time DEtection Transformer (RT-DETR) landed in Hugging Face transformers 🤩 with Apache 2.0 license 😍 do DETRs Beat YOLOs on Real-time Object Detection? keep reading 👀

Real-time DEtection Transformer (RT-DETR) landed in Hugging Face transformers 🤩 with Apache 2.0 license 😍 do DETRs Beat YOLOs on Real-time Object Detection? keep reading 👀

155,222 views

ViTPose -- best open-source pose estimation model just landed to Hugging Face transformers 🕺🏻💃🏻 See how to use on the next one ⤵️

ViTPose -- best open-source pose estimation model just landed to Hugging Face transformers 🕺🏻💃🏻 See how to use on the next one ⤵️

83,367 views

Meta released LongVU: a new video LM that can handle long videos (great performance, battle-tested by me ⚔) TLDR; 1️⃣ downsample using DINOv2 to eliminate redundant scenes 🦖 2️⃣ fuse rest of the features using DINOv2 and SigLIP 3️⃣ select some tokens, pass to Qwen2/Llama-3.2-3B

Meta released LongVU: a new video LM that can handle long videos (great performance, battle-tested by me ⚔) TLDR; 1️⃣ downsample using DINOv2 to eliminate redundant scenes 🦖 2️⃣ fuse rest of the features using DINOv2 and SigLIP 3️⃣ select some tokens, pass to Qwen2/Llama-3.2-3B

49,521 views

OlmOCR is a new drop by Ai2 to parse any PDF 📝🤝 I have fed one of my old master's notes and it did a great job 💗 It is based on Qwen2VL-7B and works out of the box with transformers, has Apache 2.0 license 🔥

OlmOCR is a new drop by Ai2 to parse any PDF 📝🤝 I have fed one of my old master's notes and it did a great job 💗 It is based on Qwen2VL-7B and works out of the box with transformers, has Apache 2.0 license 🔥

36,624 views

New InternVL drop with a sota 78B model with MIT license 🔥 The release comes with seven new vision LMs based on InternViT 300M/6B and Qwen2.5 and InternLM2 in different sizes ✨ 78B model is of InternViT 6B and Qwen2.5-72B Instruct, can accomplish variety of tasks 👏

New InternVL drop with a sota 78B model with MIT license 🔥 The release comes with seven new vision LMs based on InternViT 300M/6B and Qwen2.5 and InternLM2 in different sizes ✨ 78B model is of InternViT 6B and Qwen2.5-72B Instruct, can accomplish variety of tasks 👏

25,314 views

Spaces at Hugging Face is the app store of AI 📱 it's also the MCP store now 🤠 filter thousands of MCPs you can attach to your LLM 🤗

Spaces at Hugging Face is the app store of AI 📱 it's also the MCP store now 🤠 filter thousands of MCPs you can attach to your LLM 🤗

18,307 views

many parts of Hugging Face Hub is actually powered by open machine learning models 🥹 translation feature is one of them, it uses a very tiny (600M) multilingual translation model by AI at Meta 💗

many parts of Hugging Face Hub is actually powered by open machine learning models 🥹 translation feature is one of them, it uses a very tiny (600M) multilingual translation model by AI at Meta 💗

14,958 views

Aya by Cohere For AI can now see! 👀 C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! 🗣️ The authors extend Llava dataset using Aya's translation capabilities with 558k examples! works very well ⬇️

Aya by Cohere For AI can now see! 👀 C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! 🗣️ The authors extend Llava dataset using Aya's translation capabilities with 558k examples! works very well ⬇️

16,226 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

new open-source Bonsai models are out 🔥 > ternary weights in 8B (1.75 GB), 4B (0.86 GB), and 1.7B (0.37 GB) > comes in MLX, ONNX weights and WebGPU browser demo 😍 > a2.0 licensed 👏
0:49
mervenoyann's profile picture

new open-source Bonsai models are out 🔥 > ternary weights in 8B (1.75 GB), 4B (0.86 GB), and 1.7B (0.37 GB) > comes in MLX, ONNX weights and WebGPU browser demo 😍 > a2.0 licensed 👏

merve

87,324 views • 1 month ago

Microsoft released a groundbreaking model that can be used for web automation, with MIT license 🔥👏 OmniParser is a state-of-the-art UI parsing/understanding model that outperforms GPT4V in parsing. 👏
0:30
mervenoyann's profile picture

Microsoft released a groundbreaking model that can be used for web automation, with MIT license 🔥👏 OmniParser is a state-of-the-art UI parsing/understanding model that outperforms GPT4V in parsing. 👏

merve

473,069 views • 1 year ago

SAM3 is so good even cat playing didgeridoo is within distribution 🤯😂
1:07
mervenoyann's profile picture

SAM3 is so good even cat playing didgeridoo is within distribution 🤯😂

merve

103,370 views • 6 months ago

real-time vision in your browser 🔥 try out YOLO26 for pose estimation and detection built on WebGPU ⚡️
0:21
mervenoyann's profile picture

real-time vision in your browser 🔥 try out YOLO26 for pose estimation and detection built on WebGPU ⚡️

merve

46,395 views • 4 months ago

Google released MedGemma on I/O'25 👏 > 4B and 27B instruction fine-tuned vision LMs and a 4B pre-trained vision LM for medicine > available with transformers from the get-go 🤗 they also released a cool demo for scan reading ⤵️
0:25
mervenoyann's profile picture

Google released MedGemma on I/O'25 👏 > 4B and 27B instruction fine-tuned vision LMs and a 4B pre-trained vision LM for medicine > available with transformers from the get-go 🤗 they also released a cool demo for scan reading ⤵️

merve

81,287 views • 1 year ago

agents are now running Hugging Face dataset viewers 🤯
0:26
mervenoyann's profile picture

agents are now running Hugging Face dataset viewers 🤯

merve

29,784 views • 3 months ago

MatchAnything is an insane framework authors have tried to get every view that they can and dump them to modern keypoint matching models for instance you can match iphone map view to google aerial view, thermal camera views to day view even if the images are warped!
0:25
mervenoyann's profile picture

MatchAnything is an insane framework authors have tried to get every view that they can and dump them to modern keypoint matching models for instance you can match iphone map view to google aerial view, thermal camera views to day view even if the images are warped!

merve

58,133 views • 9 months ago

Google just released PaliGemma 2 Mix: new versatile instruction vision language models 🔥 > Three new models: 3B, 10B, 28B with res 224, 448 💙 > Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything 🤯
0:34
mervenoyann's profile picture

Google just released PaliGemma 2 Mix: new versatile instruction vision language models 🔥 > Three new models: 3B, 10B, 28B with res 224, 448 💙 > Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything 🤯

merve

83,701 views • 1 year ago

New 🤗 transformers release includes a very powerful Multimodel Large Language Model (MLLM) by Microsoft called KOSMOS-2! 🤩 The highlight of KOSMOS-2 is grounding, the model is *incredibly* accurate! 🌎 Play with the demo here 👉 But how does this model work? Let's take a look! 👀🧶
0:36
mervenoyann's profile picture

New 🤗 transformers release includes a very powerful Multimodel Large Language Model (MLLM) by Microsoft called KOSMOS-2! 🤩 The highlight of KOSMOS-2 is grounding, the model is *incredibly* accurate! 🌎 Play with the demo here 👉 But how does this model work? Let's take a look! 👀🧶

merve

143,816 views • 2 years ago

Lyria by Google DeepMind is next level it did average Turkish pop song very well all my Turkish friends in the conference hall was summoned lol
0:22
mervenoyann's profile picture

Lyria by Google DeepMind is next level it did average Turkish pop song very well all my Turkish friends in the conference hall was summoned lol

merve

14,752 views • 1 month ago

IBM dropped CUGA, open-source enterprise agent to automate boring tasks 🔥 > given workspace files, it writes and executes code to accomplish any task 🤯 > comes with a ton of tools built for enterprise tasks, supports MCPs > plug in your favorite LLM 👏 here's a small demo where it retrieves info from a file, calculates revenue by writing code, and drafts an e-mail 🤯 they release code, a blog and a demo 🙌🏻 you can run this locally
1:11
mervenoyann's profile picture

IBM dropped CUGA, open-source enterprise agent to automate boring tasks 🔥 > given workspace files, it writes and executes code to accomplish any task 🤯 > comes with a ton of tools built for enterprise tasks, supports MCPs > plug in your favorite LLM 👏 here's a small demo where it retrieves info from a file, calculates revenue by writing code, and drafts an e-mail 🤯 they release code, a blog and a demo 🙌🏻 you can run this locally

merve

32,866 views • 5 months ago

Chameleon 🦎 by Meta is now available in Hugging Face transformers 😍 A multimodal model that comes in 7B and 34B sizes 🤩 But what makes this model so special? keep reading ⇣
0:34
mervenoyann's profile picture

Chameleon 🦎 by Meta is now available in Hugging Face transformers 😍 A multimodal model that comes in 7B and 34B sizes 🤩 But what makes this model so special? keep reading ⇣

merve

50,221 views • 1 year ago

JUST IN: Inference Providers at Hugging Face Hub Use @FAL SambaNova Together AI Replicate on Hugging Face to infer gigantic models like DeepSeek R1 from model page or through our client SDKs (Python, JS)/HTTP calls
0:33
mervenoyann's profile picture

JUST IN: Inference Providers at Hugging Face Hub Use @FAL SambaNova Together AI Replicate on Hugging Face to infer gigantic models like DeepSeek R1 from model page or through our client SDKs (Python, JS)/HTTP calls

merve

36,875 views • 1 year ago

run AI agents in one line of CLI command 🤯 you can run tool-calling AI agents or web automation agents through CLI in smolagents get started as easily as $ webagent {prompt} in CLI tool-calling agent and more details on the next one ⬇️
0:39
mervenoyann's profile picture

run AI agents in one line of CLI command 🤯 you can run tool-calling AI agents or web automation agents through CLI in smolagents get started as easily as $ webagent {prompt} in CLI tool-calling agent and more details on the next one ⬇️

merve

35,905 views • 1 year ago

y'all know that Hugging Face Spaces is the app store of AI what you don't know is all these apps are MCP Servers thanks to Gradio MCP server 😮 plug it to your favorite provider 🤠 insanely powerful!
0:26
mervenoyann's profile picture

y'all know that Hugging Face Spaces is the app store of AI what you don't know is all these apps are MCP Servers thanks to Gradio MCP server 😮 plug it to your favorite provider 🤠 insanely powerful!

merve

19,727 views • 1 year ago

Idefics3-Llama is out! 💥 It's a multimodal model based on Llama 3.1 that accepts arbitrary number of interleaved images with text with a huge context window (10k tokens!) 😍 Link to demo and model in the next one 😏
0:37
mervenoyann's profile picture

Idefics3-Llama is out! 💥 It's a multimodal model based on Llama 3.1 that accepts arbitrary number of interleaved images with text with a huge context window (10k tokens!) 😍 Link to demo and model in the next one 😏

merve

28,014 views • 1 year ago

start agents with giants like Llama 4, with only one line of code 🔥 Hugging Face Inference Providers 🤝 smolagents
0:33
mervenoyann's profile picture

start agents with giants like Llama 4, with only one line of code 🔥 Hugging Face Inference Providers 🤝 smolagents

merve

19,267 views • 1 year ago

IN: video fine-tuning support for AI at Meta's V-JEPA 2 in HF transformers 🔥 it comes with > fine-tuning notebook > four models fine-tuned on Diving48 and SSv2 dataset > FastRTC demo on V-JEPA2 SSv2 (see below) we're looking forward to see fine-tuned V-JEPA2 models on Hub ⏯️
0:36
mervenoyann's profile picture

IN: video fine-tuning support for AI at Meta's V-JEPA 2 in HF transformers 🔥 it comes with > fine-tuning notebook > four models fine-tuned on Diving48 and SSv2 dataset > FastRTC demo on V-JEPA2 SSv2 (see below) we're looking forward to see fine-tuned V-JEPA2 models on Hub ⏯️

merve

15,625 views • 11 months ago

have you played with Gemma 3-12B-IT on Hugging Face Spaces yet? 😏 you can also pull this and run locally if you feel like it 🤝 here's me asking Gemma 3 for styling tips (interleaved inference) 👒
0:51
mervenoyann's profile picture

have you played with Gemma 3-12B-IT on Hugging Face Spaces yet? 😏 you can also pull this and run locally if you feel like it 🤝 here's me asking Gemma 3 for styling tips (interleaved inference) 👒

merve

17,275 views • 1 year ago

stop using VLMs blindly ✋🏻 compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) 🔥 > has support for multiple VLMs: Gemma 3, Qwen2.5VL, Llama4 > recommend us new models or inputs, we'll add 🫡
0:57
mervenoyann's profile picture

stop using VLMs blindly ✋🏻 compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) 🔥 > has support for multiple VLMs: Gemma 3, Qwen2.5VL, Llama4 > recommend us new models or inputs, we'll add 🫡

merve

13,154 views • 11 months ago