Hugging Face's logo

carbon
Team
non-profit
Activity Feed

AI & ML interests

None defined yet.
cgeorgiawย 
posted an update 3 months ago
abidlabsย 
authored 3 papers 3 months ago
abidlabsย 
posted an update 3 months ago
view post
Post
9520
Why I think local, open-source models will eventually win.

The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.

In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.

An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly โ€œsmarterโ€ closed model that has to make remote API calls for every move.

Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users wonโ€™t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are โ€œgood enoughโ€ and the expectation will shift toward everything running locally. Itโ€™ll happen sooner than most people think.
ยท
merveย 
posted an update 4 months ago
view post
Post
8630
deepseek-ai/DeepSeek-OCR is out! ๐Ÿ”ฅ my take โคต๏ธ
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
ยท
lvwerraย 
authored a paper 4 months ago
abidlabsย 
posted an update 4 months ago
merveย 
posted an update 5 months ago
view post
Post
6874
large AI labs open-sourced a ton of models last week ๐Ÿ”ฅ
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 ๐Ÿค
> IBM released a new Docling model with 258M params based on Granite (A2.0) ๐Ÿ“ ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana ๐ŸŒ (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset ๐Ÿ’ป OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash ๐Ÿ’ญ meituan-longcat/LongCat-Flash-Thinking
  • 2 replies
ยท
merveย 
posted an update 5 months ago
view post
Post
3442
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face ๐Ÿ”ฅ

> not only a document converter but also can do document question answering, understand multiple languages ๐Ÿคฏ
> best part: released with Apache 2.0 license ๐Ÿ‘ use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! ๐Ÿค—
> built on SigLIP2 & granite-165M

model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo ๐Ÿ’—
merveย 
posted an update 5 months ago
view post
Post
1226
a ton of image/video generation models and LLMs from big labs ๐Ÿ”ฅ

> Meta released facebook/mobilellm-r1-68c4597b104fac45f28f448e, smol LLMs for on-device use ๐Ÿ’ฌ
> Tencent released tencent/SRPO, high res image generation model and tencent/POINTS-Reader, cutting edge OCR ๐Ÿ“
> ByteDance released bytedance-research/HuMo, video generation from any input โฏ๏ธ

find more models, datasets, demos here merve/sep-11-releases-68c7dbfa26bea8cd921fa0ac
merveย 
posted an update 5 months ago
view post
Post
1031
fan-favorite vision LM Florence-2 is now officially supported in transformers ๐Ÿค—

find all the models in
florence-community org ๐Ÿซก
merveย 
posted an update 5 months ago
merveย 
posted an update 5 months ago
cgeorgiawย 
posted an update 5 months ago
view post
Post
6020
๐Ÿš€๐Ÿš€๐Ÿš€ The largest ever dataset of co-folded 3D protein-ligand structures just dropped on HF!!

Meet SAIR (Structurally Augmented ICโ‚…โ‚€ Repository): 5M+ AI-generated complexes with experimentally measured drug potency data from SandboxAQ. ๐Ÿš€๐Ÿš€๐Ÿš€

Check it out and explore here: SandboxAQ/SAIR

ยท
merveย 
posted an update 5 months ago
view post
Post
6299
large AI labs have dropped so many open models last week ๐Ÿ”ฅ don't miss out on them

โ†’ Apple released on-device vision LMs apple/fastvlm-68ac97b9cd5cacefdd04872e & apple/mobileclip2-68ac947dcb035c54bcd20c47
โ†’ OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) OpenGVLab/internvl35-68ac87bd52ebe953485927fb
โ†’ MSFT released a killer small TTS model (OS) microsoft/VibeVoice-1.5B

find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486
  • 1 reply
ยท
merveย 
posted an update 5 months ago
view post
Post
6087
first vision language model built off openai/gpt-oss-20b just dropped! ๐Ÿ”ฅ

InternVL3.5 comes with 32 models ๐Ÿคฏ pre-trained, fine-tuned, aligned in various sizes OpenGVLab/internvl35-68ac87bd52ebe953485927fb
comes with gpt-oss or Qwen3 for LLM part โคต๏ธ
  • 1 reply
ยท
cgeorgiawย 
posted an update 6 months ago
merveย 
posted an update 6 months ago
view post
Post
3335
GPT-4.1-mini level model right in your iPhone ๐Ÿคฏ

openbmb/MiniCPM-V-4 is only 4B while surpassing GPT-4.1-mini in vision benchmarks ๐Ÿ”ฅ

allows commercial use as well!
merveย 
posted an update 6 months ago
view post
Post
1198
we're all sleeping on this OCR model rednote-hilab/dots.ocr ๐Ÿ”ฅ

dots.ocr is a new 3B model with sota performance, support for 100 languages & allowing commercial use! ๐Ÿคฏ

single e2e model to extract image, convert tables, formula, and more into markdown ๐Ÿ“
try it MohamedRashad/Dots-OCR