SmolLM - blazingly fast and remarkably powerful
โข
299
Loubna Ben Allal
loubnabnl
AI & ML interests
SmolLMs, ML for code, data
Recent Activity
published
a model
34 minutes ago
HuggingFaceH4/Qwen2.5-1.5B-Instruct-Bespoke-3e5
published
a model
about 1 hour ago
HuggingFaceH4/SmolLM2-1.7B-Instruct-Bespoke-3e5
Articles
Organizations
loubnabnl's activity
reacted to
lewtun's
post with ๐ฅ
about 20 hours ago
Post
4168
We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open!
๐งช Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.
๐ง Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.
๐ฅ Step 3: show we can go from base model -> SFT -> RL via multi-stage training.
Follow along: https://github.com/huggingface/open-r1
๐งช Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.
๐ง Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.
๐ฅ Step 3: show we can go from base model -> SFT -> RL via multi-stage training.
Follow along: https://github.com/huggingface/open-r1
- 1 reply
reacted to
ginipick's
post with ๐ฅ
about 1 month ago
Post
4341
๐ Digital Odyssey: AI Image & Video Generation Platform ๐จ
Welcome to our all-in-one AI platform for image and video generation! ๐
โจ Key Features
๐จ High-quality image generation from text
๐ฅ Video creation from still images
๐ Multi-language support with automatic translation
๐ ๏ธ Advanced customization options
๐ซ Unique Advantages
โก Fast and accurate results using FLUX.1-dev and Hyper-SD models
๐ Robust content safety filtering system
๐ฏ Intuitive user interface
๐ ๏ธ Extended toolkit including image upscaling and logo generation
๐ฎ How to Use
Enter your image or video description
Adjust settings as needed
Click generate
Save and share your results automatically
๐ง Tech Stack
FluxPipeline
Gradio
PyTorch
OpenCV
link: ginigen/Dokdo
Turn your imagination into reality with AI! โจ
#AI #ImageGeneration #VideoGeneration #MachineLearning #CreativeTech
Welcome to our all-in-one AI platform for image and video generation! ๐
โจ Key Features
๐จ High-quality image generation from text
๐ฅ Video creation from still images
๐ Multi-language support with automatic translation
๐ ๏ธ Advanced customization options
๐ซ Unique Advantages
โก Fast and accurate results using FLUX.1-dev and Hyper-SD models
๐ Robust content safety filtering system
๐ฏ Intuitive user interface
๐ ๏ธ Extended toolkit including image upscaling and logo generation
๐ฎ How to Use
Enter your image or video description
Adjust settings as needed
Click generate
Save and share your results automatically
๐ง Tech Stack
FluxPipeline
Gradio
PyTorch
OpenCV
link: ginigen/Dokdo
Turn your imagination into reality with AI! โจ
#AI #ImageGeneration #VideoGeneration #MachineLearning #CreativeTech
- 7 replies
reacted to
anton-l's
post with ๐๐ฅ
about 1 month ago
Post
2288
Introducing ๐๐
๐ข๐ง๐๐๐๐ญ๐ก: the best public math pre-training dataset with 50B+ tokens!
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
๐ ๏ธ carefully extracting math data from Common Crawl;
๐ iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! ๐
Weโre also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
๐ ๏ธ carefully extracting math data from Common Crawl;
๐ iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! ๐
Weโre also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
reacted to
julien-c's
post with ๐ฅโค๏ธ๐ค
about 2 months ago
Post
8744
After some heated discussion ๐ฅ, we clarify our intent re. storage limits on the Hub
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co./docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community ๐ฅ
cc: @reach-vb @pierric @victor and the HF team
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co./docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community ๐ฅ
cc: @reach-vb @pierric @victor and the HF team
- 28 replies
reacted to
clem's
post with ๐ฅโค๏ธ
about 2 months ago
Post
4403
Hugging Face is becoming the best place to share the most viral AI apps with spaces.
Kolors Virtual Try-on just crossed 6,000,000 unique visitors & is now the #5 most popular space. Congrats to the Kwai Kolors team!
Kwai-Kolors/Kolors-Virtual-Try-On
Kolors Virtual Try-on just crossed 6,000,000 unique visitors & is now the #5 most popular space. Congrats to the Kwai Kolors team!
Kwai-Kolors/Kolors-Virtual-Try-On
- 2 replies
reacted to
merve's
post with ๐ฅ
about 2 months ago
Post
2913
Last week we were blessed with open-source models! A recap ๐
merve/nov-29-releases-674ccc255a57baf97b1e2d31
๐ผ๏ธ Multimodal
> At Hugging Face we released SmolVLM, a performant and efficient smol vision language model ๐
> Show Lab released ShowUI-2B: new vision-language-action model to build GUI/web automation agents ๐ค
> Rhymes AI has released the base model of Aria: Aria-Base-64K and Aria-Base-8K with their respective context length
> ViDoRe team released ColSmolVLM: A new ColPali-like retrieval model based on SmolVLM
> Dataset: Llava-CoT-o1-Instruct: new dataset labelled using Llava-CoT multimodal reasoning model๐
> Dataset: LLaVA-CoT-100k dataset used to train Llava-CoT released by creators of Llava-CoT ๐
๐ฌ LLMs
> Qwen team released QwQ-32B-Preview, state-of-the-art open-source reasoning model, broke the internet ๐ฅ
> AliBaba has released Marco-o1, a new open-source reasoning model ๐ฅ
> NVIDIA released Hymba 1.5B Base and Instruct, the new state-of-the-art SLMs with hybrid architecture (Mamba + transformer)
โฏ๏ธ Image/Video Generation
> Qwen2VL-Flux: new image generation model based on Qwen2VL image encoder, T5 and Flux for generation
> Lightricks released LTX-Video, a new DiT-based video generation model that can generate 24 FPS videos at 768x512 res โฏ๏ธ
> Dataset: Image Preferences is a new image generation preference dataset made with DIBT community effort of Argilla ๐ท๏ธ
Audio
> OuteAI released OuteTTS-0.2-500M new multilingual text-to-speech model based on Qwen-2.5-0.5B trained on 5B audio prompt tokens
merve/nov-29-releases-674ccc255a57baf97b1e2d31
๐ผ๏ธ Multimodal
> At Hugging Face we released SmolVLM, a performant and efficient smol vision language model ๐
> Show Lab released ShowUI-2B: new vision-language-action model to build GUI/web automation agents ๐ค
> Rhymes AI has released the base model of Aria: Aria-Base-64K and Aria-Base-8K with their respective context length
> ViDoRe team released ColSmolVLM: A new ColPali-like retrieval model based on SmolVLM
> Dataset: Llava-CoT-o1-Instruct: new dataset labelled using Llava-CoT multimodal reasoning model๐
> Dataset: LLaVA-CoT-100k dataset used to train Llava-CoT released by creators of Llava-CoT ๐
๐ฌ LLMs
> Qwen team released QwQ-32B-Preview, state-of-the-art open-source reasoning model, broke the internet ๐ฅ
> AliBaba has released Marco-o1, a new open-source reasoning model ๐ฅ
> NVIDIA released Hymba 1.5B Base and Instruct, the new state-of-the-art SLMs with hybrid architecture (Mamba + transformer)
โฏ๏ธ Image/Video Generation
> Qwen2VL-Flux: new image generation model based on Qwen2VL image encoder, T5 and Flux for generation
> Lightricks released LTX-Video, a new DiT-based video generation model that can generate 24 FPS videos at 768x512 res โฏ๏ธ
> Dataset: Image Preferences is a new image generation preference dataset made with DIBT community effort of Argilla ๐ท๏ธ
Audio
> OuteAI released OuteTTS-0.2-500M new multilingual text-to-speech model based on Qwen-2.5-0.5B trained on 5B audio prompt tokens
reacted to
julien-c's
post with ๐๐ฅ
about 2 months ago
Post
2829
wow ๐ฎ
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
PrimeIntellect/INTELLECT-1-Instruct
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
PrimeIntellect/INTELLECT-1-Instruct
reacted to
merve's
post with ๐ฅ
2 months ago
Post
3929
Small yet mighty! ๐ซ
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient ๐ค
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO ๐
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO ๐
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient ๐ค
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO ๐
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO ๐
reacted to
thomwolf's
post with ๐ฅ
2 months ago
Post
1705
Interesting long read from
@evanmiller-anthropic
on having a better founded statistical approach to Language Model Evaluations:
https://www.anthropic.com/research/statistical-approach-to-model-evals
Worth a read if you're into LLM evaluations!
Cc @clefourrier
https://www.anthropic.com/research/statistical-approach-to-model-evals
Worth a read if you're into LLM evaluations!
Cc @clefourrier
- 1 reply
reacted to
openfree's
post with ๐๐ฅ
2 months ago
Post
3172
๐ค HuggingFace Trending TOP 300 Board - Featuring AI Rating System
๐ Service Introduction
A comprehensive dashboard that provides at-a-glance access to the real-time TOP 300 trending Spaces, Models, and Datasets on HuggingFace.
Our specially developed AI rating system evaluates the practical value and growth potential of each item.
โญ Key Features
1. AI Rising Rate
Growth potential evaluation based on creation date and ranking
5-tier star rating system (โ โ โ โ โ )
Evaluation Criteria:
Recency: Higher relative weights for recently created items
Ranking Impact: Higher relative weights for top rankings
Comprehensive assessment using statistical/analytical models applied to AI
2. AI Popularity Score
Comprehensive evaluation combining objective popularity and Rising Rate
18-tier grading system from AAA+ to B-
Evaluation Elements:
Base Score: Benchmark based on likes, downloads, comments, etc.
Additional Score: Rising Rate applied as a weighted factor
Comprehensive assessment using statistical/analytical models applied to AI
3. Visualization Features
Real-time screenshot capture with caching
Intuitive card-based UI
Responsive grid layout
Pastel gradient design
๐ฏ Applications
AI/ML Project Trend Analysis
Early Discovery of Promising Models/Datasets
Community Activity Monitoring
Research/Development Direction Reference
๐ก Key Advantages
Real-time TOP 300 ranking
AI-based objective evaluation system
Fast loading with caching system
Intuitive and modern UI/UX
Integrated dashboard for 3 categories
๐ Update Cycle
Real-time data reflection
Manual refresh option
Minimized server load through screenshot caching
๐ Future Plans
Addition of detailed analysis report feature
Custom filtering options
Time-series trend analysis
Category-specific detailed statistics
๐ How to Access
openfree/trending-board
#HuggingFace #AI #MachineLearning #TrendingBoard #DataScience #
๐ Service Introduction
A comprehensive dashboard that provides at-a-glance access to the real-time TOP 300 trending Spaces, Models, and Datasets on HuggingFace.
Our specially developed AI rating system evaluates the practical value and growth potential of each item.
โญ Key Features
1. AI Rising Rate
Growth potential evaluation based on creation date and ranking
5-tier star rating system (โ โ โ โ โ )
Evaluation Criteria:
Recency: Higher relative weights for recently created items
Ranking Impact: Higher relative weights for top rankings
Comprehensive assessment using statistical/analytical models applied to AI
2. AI Popularity Score
Comprehensive evaluation combining objective popularity and Rising Rate
18-tier grading system from AAA+ to B-
Evaluation Elements:
Base Score: Benchmark based on likes, downloads, comments, etc.
Additional Score: Rising Rate applied as a weighted factor
Comprehensive assessment using statistical/analytical models applied to AI
3. Visualization Features
Real-time screenshot capture with caching
Intuitive card-based UI
Responsive grid layout
Pastel gradient design
๐ฏ Applications
AI/ML Project Trend Analysis
Early Discovery of Promising Models/Datasets
Community Activity Monitoring
Research/Development Direction Reference
๐ก Key Advantages
Real-time TOP 300 ranking
AI-based objective evaluation system
Fast loading with caching system
Intuitive and modern UI/UX
Integrated dashboard for 3 categories
๐ Update Cycle
Real-time data reflection
Manual refresh option
Minimized server load through screenshot caching
๐ Future Plans
Addition of detailed analysis report feature
Custom filtering options
Time-series trend analysis
Category-specific detailed statistics
๐ How to Access
openfree/trending-board
#HuggingFace #AI #MachineLearning #TrendingBoard #DataScience #
- 3 replies
posted
an
update
2 months ago
Post
2016
Making SmolLM2 reproducible: open-sourcing our training & evaluation toolkit ๐ ๏ธ https://github.com/huggingface/smollm/
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
reacted to
prithivMLmods's
post with ๐ฅ
2 months ago
Post
2921
Weekend Dribble ๐ฆ๐บ
Adapters for Product Ad Backdrops, Smooth Polaroids, Minimalist Sketch cards, Super Blends!!
๐คDemo on: prithivMLmods/FLUX-LoRA-DLC
Stranger Zones :
๐๐ผ{ Super Blend } : strangerzonehf/Flux-Super-Blend-LoRA
๐๐ผ{ Product Concept Ad } : prithivMLmods/Flux-Product-Ad-Backdrop
๐๐ผ{ Frosted Mock-ups } : prithivMLmods/Flux.1-Dev-Frosted-Container-LoRA
๐๐ผ{ Polaroid Plus } : prithivMLmods/Flux-Polaroid-Plus
๐๐ผ{Sketch Cards} : prithivMLmods/Flux.1-Dev-Sketch-Card-LoRA
๐Stranger Zone: https://huggingface.co./strangerzonehf
๐Flux LoRA Collections: prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
.
.
.
@prithivMLmods ๐ค
Adapters for Product Ad Backdrops, Smooth Polaroids, Minimalist Sketch cards, Super Blends!!
๐คDemo on: prithivMLmods/FLUX-LoRA-DLC
Stranger Zones :
๐๐ผ{ Super Blend } : strangerzonehf/Flux-Super-Blend-LoRA
๐๐ผ{ Product Concept Ad } : prithivMLmods/Flux-Product-Ad-Backdrop
๐๐ผ{ Frosted Mock-ups } : prithivMLmods/Flux.1-Dev-Frosted-Container-LoRA
๐๐ผ{ Polaroid Plus } : prithivMLmods/Flux-Polaroid-Plus
๐๐ผ{Sketch Cards} : prithivMLmods/Flux.1-Dev-Sketch-Card-LoRA
๐Stranger Zone: https://huggingface.co./strangerzonehf
๐Flux LoRA Collections: prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
.
.
.
@prithivMLmods ๐ค
reacted to
merve's
post with โค๏ธ๐
2 months ago
Post
3191
your hugging face profile now has your recent activities ๐ค