Not sure since I didn't participate in the project, but the whole point is for it to be less intense than actually generating images. I guess the cost is generating the tokens.
Andres Marafioti
andito
AI & ML interests
Multimodal models, VLM and TTS
Recent Activity
updated
a model
12 minutes ago
andito/nanoVLM
liked
a dataset
1 day ago
Apollo-LMMs/TimeScope
liked
a model
2 days ago
HuggingFaceTB/SmolLM3-3B
Organizations
replied to
their
post
4 days ago
replied to
their
post
4 days ago
posted
an
update
9 days ago
Post
3859
🧠👁️ Can AI visualize solutions?
Humans often solve visual problems by sketching ideas in our minds. What if Vision-Language Models (VLMs) could do something similar, not by generating full images, but by using internal “mental sketches”?
That’s the idea behind Mirage, a new framework that empowers VLMs to reason using latent visual tokens. Instead of just thinking in words, Mirage mixes in abstract visual representations that help the model solve complex tasks.
These aren't photorealistic images. They're compact, internal representations optimized purely to support reasoning.
🔧 Mirage is trained in two phases:
1) Grounding: It learns to produce latent tokens anchored in real images.
2) Refinement: The model drops the images and learns to generate visual tokens on its own.
📈 And yes, it works!
On challenging benchmarks like Visual Spatial Planning, Jigsaw puzzles, and Spatial Attention Tasks, Mirage clearly outperforms GPT-4o and other strong baselines.
Smart sketches > empty words.
By mimicking the way humans visualize solutions, Mirage gives AI a new kind of imagination, one that’s faster, more efficient, and more human-like.
Kudos to the teams at UMass Amherst and MIT behind this exciting work.
Check the paper: Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (2506.17218)
Humans often solve visual problems by sketching ideas in our minds. What if Vision-Language Models (VLMs) could do something similar, not by generating full images, but by using internal “mental sketches”?
That’s the idea behind Mirage, a new framework that empowers VLMs to reason using latent visual tokens. Instead of just thinking in words, Mirage mixes in abstract visual representations that help the model solve complex tasks.
These aren't photorealistic images. They're compact, internal representations optimized purely to support reasoning.
🔧 Mirage is trained in two phases:
1) Grounding: It learns to produce latent tokens anchored in real images.
2) Refinement: The model drops the images and learns to generate visual tokens on its own.
📈 And yes, it works!
On challenging benchmarks like Visual Spatial Planning, Jigsaw puzzles, and Spatial Attention Tasks, Mirage clearly outperforms GPT-4o and other strong baselines.
Smart sketches > empty words.
By mimicking the way humans visualize solutions, Mirage gives AI a new kind of imagination, one that’s faster, more efficient, and more human-like.
Kudos to the teams at UMass Amherst and MIT behind this exciting work.
Check the paper: Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (2506.17218)
-
- 4 replies
reacted to
merve's
post with 🚀
24 days ago
Post
3621
Releases of the past week are here
merve/releases-june-13-6852c3c1eaf1e0c24c958860
Here's our picks 🤓
So many interesting models released past week in open AI! 🤖
🖼️ Computer Vision/VLMs
> nanonets/Nanonets-OCR-s is the new state-of-the-art OCR model that can handle checkboxes, watermarks, tables (OS)
> Meta released facebook/v-jepa-2-6841bad8413014e185b497a6, new sota video embeddings with two new classification models (OS)
> ByteDance-Seed/SeedVR2-3B is a new 3B video restoration model (OS)
Audio
> Stepfun released stepfun-ai/Step-Audio-AQAA, new large (137B 🤯) audio language model that takes in audio and generates audio (OS)
🤖 Robotics
> nvidia released nvidia/GR00T-N1.5-3B, new open foundation vision language action model
3D
> tencent/Hunyuan3D-2.1 is the new version of Hunyuan by Tencent that can generate 3D assets from text and image prompts
Here's our picks 🤓
So many interesting models released past week in open AI! 🤖
🖼️ Computer Vision/VLMs
> nanonets/Nanonets-OCR-s is the new state-of-the-art OCR model that can handle checkboxes, watermarks, tables (OS)
> Meta released facebook/v-jepa-2-6841bad8413014e185b497a6, new sota video embeddings with two new classification models (OS)
> ByteDance-Seed/SeedVR2-3B is a new 3B video restoration model (OS)
Audio
> Stepfun released stepfun-ai/Step-Audio-AQAA, new large (137B 🤯) audio language model that takes in audio and generates audio (OS)
🤖 Robotics
> nvidia released nvidia/GR00T-N1.5-3B, new open foundation vision language action model
3D
> tencent/Hunyuan3D-2.1 is the new version of Hunyuan by Tencent that can generate 3D assets from text and image prompts
reacted to
danaaubakirova's
post with ❤️
about 1 month ago
Post
2254
We just dropped SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics!
check out the blog: https://huggingface.co/blog/smolvla
read the technical report: SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics (2506.01844)
access the model weights: lerobot/smolvla_base
check out the blog: https://huggingface.co/blog/smolvla
read the technical report: SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics (2506.01844)
access the model weights: lerobot/smolvla_base
reacted to
merve's
post with 🤗
4 months ago
Post
4323
So many open releases at Hugging Face past week 🤯 recapping all here ⤵️
merve/march-21-releases-67dbe10e185f199e656140ae
👀 Multimodal
> Mistral AI released a 24B vision LM, both base and instruction FT versions, sota 🔥 (OS)
> with IBM we released SmolDocling, a sota 256M document parser with Apache 2.0 license (OS)
> SpatialLM is a new vision LM that outputs 3D bounding boxes, comes with 0.5B (QwenVL based) and 1B (Llama based) variants
> SkyWork released SkyWork-R1V-38B, new vision reasoning model (OS)
💬 LLMs
> NVIDIA released new Nemotron models in 49B and 8B with their post-training dataset
> LG released EXAONE, new reasoning models in 2.4B, 7.8B and 32B
> Dataset: Glaive AI released a new reasoning dataset of 22M+ examples
> Dataset: NVIDIA released new helpfulness dataset HelpSteer3
> Dataset: OpenManusRL is a new agent dataset based on ReAct framework (OS)
> Open-R1 team released OlympicCoder, new competitive coder model in 7B and 32B
> Dataset: GeneralThought-430K is a new reasoning dataset (OS)
🖼️ Image Generation/Computer Vision
> Roboflow released RF-DETR, new real-time sota object detector (OS) 🔥
> YOLOE is a new real-time zero-shot object detector with text and visual prompts 🥹
> Stability AI released Stable Virtual Camera, a new novel view synthesis model
> Tencent released Hunyuan3D-2mini, new small and fast 3D asset generation model
> ByteDance released InfiniteYou, new realistic photo generation model
> StarVector is a new 8B model that generates svg from images
> FlexWorld is a new model that expands 3D views (OS)
🎤 Audio
> Sesame released CSM-1B new speech generation model (OS)
🤖 Robotics
> NVIDIA released GR00T, new robotics model for generalized reasoning and skills, along with the dataset
*OS ones have Apache 2.0 or MIT license
👀 Multimodal
> Mistral AI released a 24B vision LM, both base and instruction FT versions, sota 🔥 (OS)
> with IBM we released SmolDocling, a sota 256M document parser with Apache 2.0 license (OS)
> SpatialLM is a new vision LM that outputs 3D bounding boxes, comes with 0.5B (QwenVL based) and 1B (Llama based) variants
> SkyWork released SkyWork-R1V-38B, new vision reasoning model (OS)
💬 LLMs
> NVIDIA released new Nemotron models in 49B and 8B with their post-training dataset
> LG released EXAONE, new reasoning models in 2.4B, 7.8B and 32B
> Dataset: Glaive AI released a new reasoning dataset of 22M+ examples
> Dataset: NVIDIA released new helpfulness dataset HelpSteer3
> Dataset: OpenManusRL is a new agent dataset based on ReAct framework (OS)
> Open-R1 team released OlympicCoder, new competitive coder model in 7B and 32B
> Dataset: GeneralThought-430K is a new reasoning dataset (OS)
🖼️ Image Generation/Computer Vision
> Roboflow released RF-DETR, new real-time sota object detector (OS) 🔥
> YOLOE is a new real-time zero-shot object detector with text and visual prompts 🥹
> Stability AI released Stable Virtual Camera, a new novel view synthesis model
> Tencent released Hunyuan3D-2mini, new small and fast 3D asset generation model
> ByteDance released InfiniteYou, new realistic photo generation model
> StarVector is a new 8B model that generates svg from images
> FlexWorld is a new model that expands 3D views (OS)
🎤 Audio
> Sesame released CSM-1B new speech generation model (OS)
🤖 Robotics
> NVIDIA released GR00T, new robotics model for generalized reasoning and skills, along with the dataset
*OS ones have Apache 2.0 or MIT license
posted
an
update
4 months ago
Post
2975
Extremely bullish on
@CohereForAI
's Aya Vision (8B & 32B) - new SOTA open-weight VLMs
- 8B wins up to 81% of the time in its class, better than Gemini Flash
- 32B beats Llama 3.2 90B!
- Covers 23 languages, excels in image captioning, VQA & more
- Integrated on transformers from Day 0!
Efficient multimodal models are here to stay!!🔥
Check out their blog! https://huggingface.co/blog/aya-vision
- 8B wins up to 81% of the time in its class, better than Gemini Flash
- 32B beats Llama 3.2 90B!
- Covers 23 languages, excels in image captioning, VQA & more
- Integrated on transformers from Day 0!
Efficient multimodal models are here to stay!!🔥
Check out their blog! https://huggingface.co/blog/aya-vision
posted
an
update
6 months ago
Post
1657
𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝘁𝗵𝗲 𝘄𝗼𝗿𝗹𝗱'𝘀 𝘀𝗺𝗮𝗹𝗹𝗲𝘀𝘁 𝘃𝗶𝘀𝗶𝗼𝗻 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗺𝗼𝗱𝗲𝗹!
We’re thrilled to share 𝗦𝗺𝗼𝗹𝗩𝗟𝗠 (256M & 500M)—the smallest Visual Language Models ever built. Think: running on <1GB of GPU memory—you can fine-tune it on your laptop and run it on your toaster!
Why It’s Game-Changing:
- 𝗢𝘂𝘁𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝘀 𝗟𝗮𝗿𝗴𝗲𝗿 𝗠𝗼𝗱𝗲𝗹𝘀: Even the 256M model surpasses our SOTA 80B-parameter model from just 17 months ago. Over 300x reduction!
𝗠𝗶𝗴𝗵𝘁𝘆 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝗰𝘆: The 256M version delivers 80% of our 2.2B model’s performance, and the 500M version hits 90%
𝗟𝗶𝗴𝗵𝘁𝗻𝗶𝗻𝗴-𝗙𝗮𝘀𝘁 𝗦𝗲𝗮𝗿𝗰𝗵: SmolVLM integrates with ColiPali for state-of-the-art retrieval speeds—on par with models 10x bigger. That means cheaper, faster indexing and real-world impact.
What’s New Under the Hood:
- 𝗡𝗲𝘄 𝗩𝗶𝘀𝗶𝗼𝗻 𝗘𝗻𝗰𝗼𝗱𝗲𝗿: Smaller overall size (400M -> 93M), but with higher resolution.
- 𝗛𝗶𝗴𝗵𝗲𝗿 𝗣𝗶𝘅𝗲𝗹𝘀/𝗧𝗼𝗸𝗲𝗻: 4096 vs. 1820—more efficient image processing.
- 𝗦𝗺𝗮𝗿𝘁 𝗧𝗼𝗸𝗲𝗻𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Faster training and a performance boost.
Check our blog: https://huggingface.co/blog/smolervlm
The models: HuggingFaceTB/smolvlm-256m-and-500m-6791fafc5bb0ab8acc960fb0
The demo: HuggingFaceTB/SmolVLM-256M-Demo
We’re thrilled to share 𝗦𝗺𝗼𝗹𝗩𝗟𝗠 (256M & 500M)—the smallest Visual Language Models ever built. Think: running on <1GB of GPU memory—you can fine-tune it on your laptop and run it on your toaster!
Why It’s Game-Changing:
- 𝗢𝘂𝘁𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝘀 𝗟𝗮𝗿𝗴𝗲𝗿 𝗠𝗼𝗱𝗲𝗹𝘀: Even the 256M model surpasses our SOTA 80B-parameter model from just 17 months ago. Over 300x reduction!
𝗠𝗶𝗴𝗵𝘁𝘆 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝗰𝘆: The 256M version delivers 80% of our 2.2B model’s performance, and the 500M version hits 90%
𝗟𝗶𝗴𝗵𝘁𝗻𝗶𝗻𝗴-𝗙𝗮𝘀𝘁 𝗦𝗲𝗮𝗿𝗰𝗵: SmolVLM integrates with ColiPali for state-of-the-art retrieval speeds—on par with models 10x bigger. That means cheaper, faster indexing and real-world impact.
What’s New Under the Hood:
- 𝗡𝗲𝘄 𝗩𝗶𝘀𝗶𝗼𝗻 𝗘𝗻𝗰𝗼𝗱𝗲𝗿: Smaller overall size (400M -> 93M), but with higher resolution.
- 𝗛𝗶𝗴𝗵𝗲𝗿 𝗣𝗶𝘅𝗲𝗹𝘀/𝗧𝗼𝗸𝗲𝗻: 4096 vs. 1820—more efficient image processing.
- 𝗦𝗺𝗮𝗿𝘁 𝗧𝗼𝗸𝗲𝗻𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Faster training and a performance boost.
Check our blog: https://huggingface.co/blog/smolervlm
The models: HuggingFaceTB/smolvlm-256m-and-500m-6791fafc5bb0ab8acc960fb0
The demo: HuggingFaceTB/SmolVLM-256M-Demo
- 1 reply
reacted to
AdinaY's
post with 🚀
6 months ago
Post
3333
What happened yesterday in the Chinese AI community? 🚀
T2A-01-HD 👉 https://hailuo.ai/audio
MiniMax's Text-to-Audio model, now in Hailuo AI, offers 300+ voices in 17+ languages and instant emotional voice cloning.
Tare 👉 https://www.trae.ai/
A new coding tool by Bytedance for professional developers, supporting English & Chinese with free access to Claude 3.5 and GPT-4 for a limited time.
DeepSeek-R1 Series 👉 deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d
Open-source reasoning models with MIT license by DeepSeek.
Kimi K 1.5 👉 https://github.com/MoonshotAI/Kimi-k1.5 | https://kimi.ai/
An O1-level multi-modal model by MoonShot AI, utilizing reinforcement learning with long and short-chain-of-thought and supporting up to 128k tokens.
And today…
Hunyuan 3D-2.0 👉 tencent/Hunyuan3D-2
A SoTA 3D synthesis system for high-res textured assets by Tencent Hunyuan , with open weights and code!
Stay tuned for more updates 👉
zh-ai-community
T2A-01-HD 👉 https://hailuo.ai/audio
MiniMax's Text-to-Audio model, now in Hailuo AI, offers 300+ voices in 17+ languages and instant emotional voice cloning.
Tare 👉 https://www.trae.ai/
A new coding tool by Bytedance for professional developers, supporting English & Chinese with free access to Claude 3.5 and GPT-4 for a limited time.
DeepSeek-R1 Series 👉 deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d
Open-source reasoning models with MIT license by DeepSeek.
Kimi K 1.5 👉 https://github.com/MoonshotAI/Kimi-k1.5 | https://kimi.ai/
An O1-level multi-modal model by MoonShot AI, utilizing reinforcement learning with long and short-chain-of-thought and supporting up to 128k tokens.
And today…
Hunyuan 3D-2.0 👉 tencent/Hunyuan3D-2
A SoTA 3D synthesis system for high-res textured assets by Tencent Hunyuan , with open weights and code!
Stay tuned for more updates 👉
zh-ai-community
reacted to
clem's
post with 🚀
7 months ago
Post
2148
Coming back to Paris Friday to open our new Hugging Face office!
We're at capacity for the party but add your name in the waiting list as we're trying to privatize the passage du Caire for extra space for robots 🤖🦾🦿
https://t.co/enkFXjWndJ
We're at capacity for the party but add your name in the waiting list as we're trying to privatize the passage du Caire for extra space for robots 🤖🦾🦿
https://t.co/enkFXjWndJ
- 1 reply
reacted to
sayakpaul's
post with 🚀
7 months ago
Post
2276
In the past seven days, the Diffusers team has shipped:
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
- 1 reply
reacted to
merve's
post with 🔥
7 months ago
Post
2851
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!
ry it here kkr5155/maya_demo
Dataset maya-multimodal/pretrain
Model maya-multimodal/maya 👏
kudos @nahidalam and team
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!
ry it here kkr5155/maya_demo
Dataset maya-multimodal/pretrain
Model maya-multimodal/maya 👏
kudos @nahidalam and team
-
- 1 reply
reacted to
merve's
post with ❤️
7 months ago
Post
5684
This week in open-source AI was insane 🤠 A small recap🕺🏻
merve/dec-6-releases-67545caebe9fc4776faac0a3
Multimodal 🖼️
> Google shipped a PaliGemma 2, new iteration of PaliGemma with more sizes: 3B, 10B and 28B, with pre-trained and captioning variants 👏
> OpenGVLab released InternVL2, seven new vision LMs in different sizes, with sota checkpoint with MIT license ✨
> Qwen team at Alibaba released the base models of Qwen2VL models with 2B, 7B and 72B ckpts
LLMs 💬
> Meta released a new iteration of Llama 70B, Llama3.2-70B trained further
> EuroLLM-9B-Instruct is a new multilingual LLM for European languages with Apache 2.0 license 🔥
> Dataset: CohereForAI released GlobalMMLU, multilingual version of MMLU with 42 languages with Apache 2.0 license
> Dataset: QwQ-LongCoT-130K is a new dataset to train reasoning models
> Dataset: FineWeb2 just landed with multilinguality update! 🔥 nearly 8TB pretraining data in many languages!
Image/Video Generation 🖼️
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux
Audio 🔊
> Indic-Parler-TTS is a new text2speech model made by community
Multimodal 🖼️
> Google shipped a PaliGemma 2, new iteration of PaliGemma with more sizes: 3B, 10B and 28B, with pre-trained and captioning variants 👏
> OpenGVLab released InternVL2, seven new vision LMs in different sizes, with sota checkpoint with MIT license ✨
> Qwen team at Alibaba released the base models of Qwen2VL models with 2B, 7B and 72B ckpts
LLMs 💬
> Meta released a new iteration of Llama 70B, Llama3.2-70B trained further
> EuroLLM-9B-Instruct is a new multilingual LLM for European languages with Apache 2.0 license 🔥
> Dataset: CohereForAI released GlobalMMLU, multilingual version of MMLU with 42 languages with Apache 2.0 license
> Dataset: QwQ-LongCoT-130K is a new dataset to train reasoning models
> Dataset: FineWeb2 just landed with multilinguality update! 🔥 nearly 8TB pretraining data in many languages!
Image/Video Generation 🖼️
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux
Audio 🔊
> Indic-Parler-TTS is a new text2speech model made by community
reacted to
fdaudens's
post with ❤️
7 months ago
Post
1138
📈👀 Just dropped: visualization mapping Hugging Face's most liked & downloaded models from 2022 to now. Small models are clearly on the rise - fascinating shift in both likes and download patterns.
Check it out: huggingface/open-source-ai-year-in-review-2024
Check it out: huggingface/open-source-ai-year-in-review-2024
reacted to
malhajar's
post with 🔥
7 months ago
Post
5223
🇫🇷 Lancement officiel de l'OpenLLM French Leaderboard : initiative open-source pour référencer l’évaluation des LLMs francophones
Après beaucoup d’efforts et de sueurs avec Alexandre Lavallee, nous sommes ravis d’annoncer que le OpenLLMFrenchLeaderboard est en ligne sur Hugging Face (space url: le-leadboard/OpenLLMFrenchLeaderboard) la toute première plateforme dédiée à l’évaluation des grands modèles de langage (LLM) en français. 🇫🇷✨
Ce projet de longue haleine est avant tout une œuvre de passion mais surtout une nécessité absolue. Il devient urgent et vital d'oeuvrer à plus de transparence dans ce domaine stratégique des LLM dits multilingues. La première pièce à l'édifice est donc la mise en place d'une évaluation systématique et systémique des modèles actuels et futurs.
Votre modèle IA français est-il prêt à se démarquer ? Soumettez le dans notre espace, et voyez comment vous vous comparez par rapport aux autres modèles.
❓ Comment ça marche :
Soumettez votre LLM français pour évaluation, et nous le testerons sur des benchmarks de référence spécifiquement adaptés pour la langue française — notre suite de benchmarks comprend :
- BBH-fr : Raisonnement complexe
- IFEval-fr : Suivi d'instructions
- GPQA-fr : Connaissances avancées
- MUSR-fr : Raisonnement narratif
- MATH_LVL5-fr : Capacités mathématiques
- MMMLU-fr : Compréhension multitâche
Le processus est encore manuel, mais nous travaillons sur son automatisation, avec le soutien de la communauté Hugging Face.
@clem , on se prépare pour une mise à niveau de l’espace ? 😏👀
Ce n'est pas qu'une question de chiffres—il s'agit de créer une IA qui reflète vraiment notre langue, notre culture et nos valeurs. OpenLLMFrenchLeaderboard est notre contribution personnelle pour façonner l'avenir des LLM en France.
Après beaucoup d’efforts et de sueurs avec Alexandre Lavallee, nous sommes ravis d’annoncer que le OpenLLMFrenchLeaderboard est en ligne sur Hugging Face (space url: le-leadboard/OpenLLMFrenchLeaderboard) la toute première plateforme dédiée à l’évaluation des grands modèles de langage (LLM) en français. 🇫🇷✨
Ce projet de longue haleine est avant tout une œuvre de passion mais surtout une nécessité absolue. Il devient urgent et vital d'oeuvrer à plus de transparence dans ce domaine stratégique des LLM dits multilingues. La première pièce à l'édifice est donc la mise en place d'une évaluation systématique et systémique des modèles actuels et futurs.
Votre modèle IA français est-il prêt à se démarquer ? Soumettez le dans notre espace, et voyez comment vous vous comparez par rapport aux autres modèles.
❓ Comment ça marche :
Soumettez votre LLM français pour évaluation, et nous le testerons sur des benchmarks de référence spécifiquement adaptés pour la langue française — notre suite de benchmarks comprend :
- BBH-fr : Raisonnement complexe
- IFEval-fr : Suivi d'instructions
- GPQA-fr : Connaissances avancées
- MUSR-fr : Raisonnement narratif
- MATH_LVL5-fr : Capacités mathématiques
- MMMLU-fr : Compréhension multitâche
Le processus est encore manuel, mais nous travaillons sur son automatisation, avec le soutien de la communauté Hugging Face.
@clem , on se prépare pour une mise à niveau de l’espace ? 😏👀
Ce n'est pas qu'une question de chiffres—il s'agit de créer une IA qui reflète vraiment notre langue, notre culture et nos valeurs. OpenLLMFrenchLeaderboard est notre contribution personnelle pour façonner l'avenir des LLM en France.
- 1 reply
reacted to
clem's
post with 🚀
7 months ago
Post
4804
Six predictions for AI in 2025 (and a review of how my 2024 predictions turned out):
- There will be the first major public protest related to AI
- A big company will see its market cap divided by two or more because of AI
- At least 100,000 personal AI robots will be pre-ordered
- China will start to lead the AI race (as a consequence of leading the open-source AI race).
- There will be big breakthroughs in AI for biology and chemistry.
- We will begin to see the economic and employment growth potential of AI, with 15M AI builders on Hugging Face.
How my predictions for 2024 turned out:
- A hyped AI company will go bankrupt or get acquired for a ridiculously low price
✅ (Inflexion, AdeptAI,...)
- Open-source LLMs will reach the level of the best closed-source LLMs
✅ with QwQ and dozens of others
- Big breakthroughs in AI for video, time-series, biology and chemistry
✅ for video 🔴for time-series, biology and chemistry
- We will talk much more about the cost (monetary and environmental) of AI
✅Monetary 🔴Environmental (😢)
- A popular media will be mostly AI-generated
✅ with NotebookLM by Google
- 10 millions AI builders on Hugging Face leading to no increase of unemployment
🔜currently 7M of AI builders on Hugging Face
- There will be the first major public protest related to AI
- A big company will see its market cap divided by two or more because of AI
- At least 100,000 personal AI robots will be pre-ordered
- China will start to lead the AI race (as a consequence of leading the open-source AI race).
- There will be big breakthroughs in AI for biology and chemistry.
- We will begin to see the economic and employment growth potential of AI, with 15M AI builders on Hugging Face.
How my predictions for 2024 turned out:
- A hyped AI company will go bankrupt or get acquired for a ridiculously low price
✅ (Inflexion, AdeptAI,...)
- Open-source LLMs will reach the level of the best closed-source LLMs
✅ with QwQ and dozens of others
- Big breakthroughs in AI for video, time-series, biology and chemistry
✅ for video 🔴for time-series, biology and chemistry
- We will talk much more about the cost (monetary and environmental) of AI
✅Monetary 🔴Environmental (😢)
- A popular media will be mostly AI-generated
✅ with NotebookLM by Google
- 10 millions AI builders on Hugging Face leading to no increase of unemployment
🔜currently 7M of AI builders on Hugging Face
- 4 replies
reacted to
davidberenstein1957's
post with 🔥
8 months ago
Post
1606
🔥 Dataset Drop - Open Image Preferences
BlackForest Labs Flux Dev VS. Stability AI Stable Diffusion Large 3.5
Together with the data-is-better-together community, we've worked on an Apache 2.0 licensed open image preference dataset based on the fal ai imgsys prompts dataset. Thanks to the awesome community, we have managed to get 5K preference pairs in less than 2 days. The annotation alignment among annotators is great too.
Aashish Kumar won a month of Hugging Face Pro by making the most contributions! Congrats from the entire team 🥇
The best thing?! We are not done yet! Let's keep the annotations coming for 5K more in the second part of the sprint! (with more prices to go around).
Dataset: https://huggingface.co/datasets/data-is-better-together/image-preferences-results
BlackForest Labs Flux Dev VS. Stability AI Stable Diffusion Large 3.5
Together with the data-is-better-together community, we've worked on an Apache 2.0 licensed open image preference dataset based on the fal ai imgsys prompts dataset. Thanks to the awesome community, we have managed to get 5K preference pairs in less than 2 days. The annotation alignment among annotators is great too.
Aashish Kumar won a month of Hugging Face Pro by making the most contributions! Congrats from the entire team 🥇
The best thing?! We are not done yet! Let's keep the annotations coming for 5K more in the second part of the sprint! (with more prices to go around).
Dataset: https://huggingface.co/datasets/data-is-better-together/image-preferences-results
posted
an
update
8 months ago
Post
1980
SmolVLM speeding locally on a laptop thanks to mlx-vlm and
@Gradio ! Try it with two lines:
pip install git+https://github.com/andimarafioti/mlx-vlm.git@stream-generate-fix
python -m mlx_vlm.chat_ui --model mlx-community/SmolVLM-Instruct-8bit
Gotta love the MLX community! Big thanks to @pcuenq and @prince_canuma !
@Gradio ! Try it with two lines:
pip install git+https://github.com/andimarafioti/mlx-vlm.git@stream-generate-fix
python -m mlx_vlm.chat_ui --model mlx-community/SmolVLM-Instruct-8bit
Gotta love the MLX community! Big thanks to @pcuenq and @prince_canuma !
reacted to
their
post with 🔥
8 months ago
Post
3405
Let's go! We are releasing SmolVLM, a smol 2B VLM built for on-device inference that outperforms all models at similar GPU RAM usage and tokens throughputs.
- SmolVLM generates tokens 7.5 to 16 times faster than Qwen2-VL! 🤯
- Other models at this size crash a laptop, but SmolVLM comfortably generates 17 tokens/sec on a macbook! 🚀
- SmolVLM can be fine-tuned on a Google collab! Or process millions of documents with a consumer GPU!
- SmolVLM even outperforms larger models in video benchmarks, despite not even being trained on videos!
Check out more!
Demo: HuggingFaceTB/SmolVLM
Blog: https://huggingface.co/blog/smolvlm
Model: HuggingFaceTB/SmolVLM-Instruct
Fine-tuning script: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
- SmolVLM generates tokens 7.5 to 16 times faster than Qwen2-VL! 🤯
- Other models at this size crash a laptop, but SmolVLM comfortably generates 17 tokens/sec on a macbook! 🚀
- SmolVLM can be fine-tuned on a Google collab! Or process millions of documents with a consumer GPU!
- SmolVLM even outperforms larger models in video benchmarks, despite not even being trained on videos!
Check out more!
Demo: HuggingFaceTB/SmolVLM
Blog: https://huggingface.co/blog/smolvlm
Model: HuggingFaceTB/SmolVLM-Instruct
Fine-tuning script: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
reacted to
merve's
post with 🔥
8 months ago
Post
2242
The authors of ColPali trained a retrieval model based on SmolVLM 🤠 https://huggingface.co/vidore/colsmolvlm-alpha
TLDR;
- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks
- ColSmolVLM is more memory efficient than ColQwen2 💗
TLDR;
- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks
- ColSmolVLM is more memory efficient than ColQwen2 💗