Hugging Face's logo

Nerdy Face
Team
company
https://huggingface.co/
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

stefan-it  authored a paper 10 days ago
The German Commons - 154 Billion Tokens of Openly Licensed Text for German Language Models
stefan-it  authored a paper about 2 months ago
Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian
JingzeShi  authored a paper 3 months ago
Trainable Dynamic Mask Sparse Attention
View all activity

prithivMLmods 
posted an update 6 days ago
Nymbo 
posted an update 8 days ago
view post
Post
1447
Two new tools added to the Nymbo/Tools MCP server, File_System and Shell_Exec. You can theoretically do basically anything with these two tools, and it should enable support for many Claude Skills.

GPT-5-Codex proves that for many cases, shell commands really are all you need, and Claude Skills seem to lean into this. The thing is, nothing about the design of Claude Skills actually restricts them to proprietary models!

# File_System

There's a new directory inside the repo called Filesystem, that's the agent's "root". It can perform the following actions : list, read, write, append, mkdir, move, copy, delete, info, help. It's able to keep this all within the scope of one tool call by making the Action field required and all other fields optional. Using a filesystem shouldn't require 15 different tools.

Files created in the public HF space live in the space's running container, and gets cleared when the space is restarted. When running the server locally, files are actually stored on disk.

# Shell_Exec

What good is a filesystem if you can't execute commands in that filesystem? This tool automatically detects if the server is running on Windows or Linux, and suggests using the appropriate shell (PowerShell/Bash). Both of these new tools require that the agent uses relative paths, rather than absolute paths. I could be convinced to back pedal on this.

# Closing Thoughts

The File_System and Shell_Exec tools aren't super polished yet, I'll continue to improve the agent's instructions and UX of using the new tools. Most of my testing was done with gpt-oss-20b and if it messes up, it gets the gist after one failed tool call. It should work perfectly fine for the GPU poor.
  • 1 reply
·
prithivMLmods 
posted an update 11 days ago
view post
Post
1859
Now you can try all the latest state-of-the-art multimodal vision-language models from the Qwen3-VL series demo on Hugging Face Spaces — including 4B, 8B, and 30B (Instruct, 4B-Thinking) variants. I’ve also uploaded the weights for the Abliterated variants of these models, up to 30B parameters. Check out the Spaces and model links below! 🤗🔥

✨ Qwen3-VL[4B,8B]: prithivMLmods/Qwen3-VL-Outpost
✨ Qwen3-VL-30B-A3B-Demo: prithivMLmods/Qwen3-VL-HF-Demo
✨ Collection: prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

Qwen3-VL Abliterated Model Collection [ Version 1.0 ]

✨ Qwen3-VL-8B-Instruct-abliterated: prithivMLmods/Qwen3-VL-8B-Instruct-abliterated
✨ Qwen3-VL-4B-Instruct-abliterated: prithivMLmods/Qwen3-VL-4B-Instruct-abliterated
✨ Qwen3-VL-8B-Thinking-abliterated: prithivMLmods/Qwen3-VL-8B-Thinking-abliterated
✨ Qwen3-VL-4B-Thinking-abliterated: prithivMLmods/Qwen3-VL-4B-Thinking-abliterated
✨ Qwen3-VL-30B-A3B-Instruct-abliterated: prithivMLmods/Qwen3-VL-30B-A3B-Instruct-abliterated
✨ Qwen3-VL-30B-A3B-Thinking-abliterated: prithivMLmods/Qwen3-VL-30B-A3B-Thinking-abliterated

⚡Collection: prithivMLmods/qwen3-vl-abliteration-oct-1625-68f0e3e567ef076594605fac

Note: This is version 1.0 of the Abliteration of the Qwen3-VL series of models. It may perform sub-optimally in some cases. If you encounter any issues, please open a discussion.
thomwolf 
authored a paper 12 days ago
prithivMLmods 
posted an update 12 days ago
view post
Post
3037
Introducing Image-Guard-2.0, an experimental, lightweight vision-language encoder model with a size of 0.1B (<100M parameters), trained on SigLIP2 (siglip2-base-patch16-224). Designed for multi-label image classification tasks, this model functions as an image safety system, serving as an image guard or moderator across a wide range of categories, from anime to realistic imagery.

⚡blog-article: https://huggingface.co/blog/prithivMLmods/image-guard-models

It also performs strict moderation and filtering of artificially synthesized content, demonstrating strong detection and handling of explicit images. Image-Guard-2.0 delivers robust performance in streamlined scenarios, ensuring reliable and effective classification across diverse visual inputs.
m-ric 
posted an update 13 days ago
view post
Post
408
Tokenization is one of the most important processes in AI - yet many would like to kill it 💀

What's tokenization? The neural networks inside LLMs actually only process numbers, not text: tokenization is the process that makes text readable for them, by converting sentences into lists of numbers.

➡️ For instance, "This is tokenization" would be split into "This | is | token | ization", then each of the parts (tokens) are converted to IDs according to a predefined mapping: for instance "ization" could map to id 2438.
Thus "This is tokenization" can become 1335 | 135 | 2980 | 2438 => now the model can process the sentence!

Most tokenizers today use pre-specified mappings called "vocabularies", generally built about the compression algorithme Byte-Pair Encoding (BPE) that learns from a big corpuses of texts an optimized split to efficiently encode any text from the same distribution into a list token IDs.

🤨 Now, these current tokenizers have flaws.
For instance, the rigidity of their mapping creates losses ; the prime example being that a tokenizer designed for English (thus optimized for tokens like "has", "been", "clock", etc) will not have the right tokens to approach Burmese, thus being terribly inefficient at it.

Many alternative approaches have emerged as a result: for instance "tokenizer-free tokenizers". One that I really liked was "entropy-based": it monitors the stream of text, and trigger a split whenever the entropy increases too much, i.e. when something "surprising" happens.

But this great article argues that tokenizers are a lesser evil. Read and decide for yourself!
https://huggingface.co/blog/catherinearnett/in-defense-of-tokenizers
Nymbo 
posted an update 13 days ago
view post
Post
1647
I've made some improvements to my custom Deep_Research tool in the Nymbo/Tools MCP server. I've added a second LLM process and it still takes less than 1 minute to complete!

The original version of my Deep_Research tool would basically dump up to 50 fetched webpages onto the Researcher model (Qwen3-235B), with only a little bit of context shown from each page.

# New "Filterer" Process

The new process includes another LLM call before the researcher process. The Filterer (also Qwen3-235B) gets the query summary and the original 50 pages with low context, and decides which pages are most relevant to the research topic. The Filterer then outputs the URLs to the relevant pages, which are then re-fetched (with more context) and sent to the Researcher.

# Researcher Context

The Researcher now gets only the relevant webpages, then begins writing the report. When testing with 50 initial results, the researcher would often end up with 10-20 results of relevant context.

It still takes less than a minute to accomplish everything, thanks entirely to Cerebras inference. It now takes about 35-45 seconds to complete once the tool is run.

It's also worth noting that both the Filterer and Researcher now are provided the current time/date before they see the content, reducing hallucinations caused by knowledge cutoffs.
prithivMLmods 
posted an update 15 days ago
view post
Post
3303
The demo of Qwen3-VL-30B-A3B-Instruct, the next-generation and powerful vision-language model in the Qwen series, delivers comprehensive upgrades across the board — including superior text understanding and generation, deeper visual perception and reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. 🤗🔥

⚡ Space / App: prithivMLmods/Qwen3-VL-HF-Demo

The model’s demo supports a wide range of tasks, including;
Image Inference, Video Inference, PDF Inference, Image Captioning (VLA), GIF Inference.

⚡ Collection: prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

Thanks for granting the blazing-fast Zero GPU access, @merve 🙏

⚡ Other Pages

> Github: https://github.com/prithivsakthiur/qwen3-vl-hf-demo
> Multimodal VLMs July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
> VL caption — < Sep 15 ’25 : prithivMLmods/vl-caption-sep-15-25-68c7f6d737985c63c13e2391
> Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd

To know more about it, visit the app page or the respective model page!!
m-ric 
posted an update 19 days ago
view post
Post
4765
STOP EVERYTHING NOW - we might finally have a radical architecture improvement over Transformers!!! 🚨

A lone scientist just proposed Tiny Recursive Model (TRM), and it is literally the most impressive model that I've seen this year.

➡️ Tiny Recursive Model is 7M parameters
➡️ On ARC-AGI, it beats flagship models like Gemini-2.5-pro

Consider how wild this is: Gemini-2.5-pro must be over 10,000x bigger
and had 1,000 as many authors 😂 (Alexia is alone on the paper)

What's this sorcery?
In short: it's a very tiny Transformers, but it loops over itself at two different frequencies, updating two latent variables: one for the proposed answer and one for the reasoning.

@AlexiaJM started from the paper Hierarchical Reasoning Model, published a few months ago, that already showed breakthrough improvement on AGI for its small size (27M)

Hierarchical Reasoning Model had introduced one main feature:
🔎 Deep supervision
In their model, one part (here one layer) would run at high frequency, and another would be lower frequency, running only every n steps.

They had used a recurrent architecture, where these layers would repeat many times ; but to make it work they had to do many approximations, including not fully backpropagating the loss through all layers.

Alexia studied what was useful and what wasn't, and cleaned the architecture as follows :
Why use a recurrent architecture, when you can just make it a loop?
➡️ She made the network recursive, looping over itself

Why use 2 latent variables ?
➡️ She provides a crystal clear explanation : the one that changes frequently is the reasoning, the one that changes at low frequency is the proposed answer.
➡️ She runs ablation studies to validate that 2 is indeed optimal.

This new setup is a much more elegant way to process reasoning than generating huge chains of tokens as all flagship models currently do.

This might be the breakthrough we've been awaiting for so long!
  • 2 replies
·
prithivMLmods 
posted an update 19 days ago
view post
Post
448
Introducing the next-gen version of DeepCaption-VLA (v2.0) — an advanced, multimodal model based on Qwen2.5-VL, specialized for Image Captioning and Vision Language Attribution (VLA). This enhanced release focuses on generating precise, attribute-rich captions that capture visual properties, object attributes, and scene details across diverse image types and aspect ratios. Version 2.0 introduces significant improvements in multilingual inference, delivering higher captioning quality and attribution accuracy in languages including Chinese (Zh), Thai (Th), and more.

🤗 DeepCaption-VLA (v2.0) : prithivMLmods/DeepCaption-VLA-V2.0-7B
🫱 Collection : prithivMLmods/vlm-20-oct-0825-68e606aa6e3993be8a3b1d51
⭐ GitHub (notebook) : https://github.com/PRITHIVSAKTHIUR/Multimodal-Outpost-Notebooks/blob/main/DeepCaption_VLA_V2_0_7B/DeepCaption_VLA_V2_0_7Bipynb.ipynb

Other Pages⚡

➥ Multimodal VLMs July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
➥ VL caption — < Sep 15 ’25 : prithivMLmods/vl-caption-sep-15-25-68c7f6d737985c63c13e2391
➥ Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd

To know more about it, visit the app page or the respective model page!!
prithivMLmods 
posted an update 20 days ago
view post
Post
2776
Have built the new Image Studio with the Gemini Image Gen models for the following multiple tasks: imagen-4.0-fast-generate-001 model for Image Generation (Text-to-Image) and Multi-Image Editing (Image-to-Image), and Draw-to-Image powered by gemini-2.5-flash-image (aka Nano Banana).

⭐ Gemini-Image-Studio: prithivMLmods/Gemini-Image-Studio (Latest)
🤞 Old-App: prithivMLmods/Nano-Banana-AIO
🥊 GitHub: https://github.com/prithivsakthiur/gemini-image-studio-hf

To proceed, you need to add your Gemini API key. Your API key is stored only for the duration of your session and will be lost when you reload or exit the page. It will not be shared or exposed anywhere.
Nymbo 
posted an update 23 days ago
view post
Post
606
I have a few Sora-2 invites - 15509N
  • 1 reply
·
prithivMLmods 
posted an update 24 days ago
view post
Post
4522
Try the Hugging Face Space demo for Logics-MLLM/Logics-Parsing, the latest multimodal VLM from the Logics Team at Alibaba Group. It enables end-to-end document parsing with precise content extraction in markdown format, and it also generates a clean HTML representation of the document while preserving its logical structure. 🤗🔥

Additionally, I’ve integrated one of my recent works — prithivMLmods/Gliese-OCR-7B-Post1.0 — which also excels at document comprehension.

⭐ Space / App : prithivMLmods/VLM-Parsing
📄 Technical Report by the Logics Team, Alibaba Group : Logics-Parsing Technical Report (2509.19760)
🖖 MM: VLM-Parsing: prithivMLmods/mm-vlm-parsing-68e33e52bfb9ae60b50602dc
⚡ Collections : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

Other Pages:

➔ Multimodal VLMs - July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
➔ Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd
➔ VL caption — < Sep 15 ’25 : prithivMLmods/vl-caption-sep-15-25-68c7f6d737985c63c13e2391

.
.
.
To know more about it, visit the app page or the respective model page!!
prithivMLmods 
posted an update 28 days ago
view post
Post
1188
Try Banana Zoom an advanced image enhancement web app that lets users select regions of an image for AI-powered upscaling and detail refinement. Using Google’s (nano banana), it analyzes selections, generates context-aware enhancements, and produces high-resolution outputs. Simply drag-and-drop or upload images, make precise or fixed-size selections, and watch improvements in real-time with smooth zoom and pixel-dissolve effects.

Space / App: prithivMLmods/Banana-Zoom
Collection: https://huggingface.co/collections/prithivMLmods/image-gen-apps-diffusion-lastupdated-09-23-68a2f4c5ef3e5e394eacc20a
GitHub: https://github.com/prithivsakthiur/banana-zoom

Your API will be automatically destroyed once you refresh the app or exit it, so each user's API will be cycled in this way.
prithivMLmods 
posted an update about 1 month ago
view post
Post
4400
Photo-Mate-i2i – a space for experimenting with adapters for image manipulation using Kontext adapters, including Photo-Restore-i2i, PhotoCleanser-i2i, Polaroid-Warm-i2i, Yarn-Photo-i2i, Monochrome-Pencil, and more. Try out the demo, and to learn more, visit the app page or the respective model pages!

⚡Demo: prithivMLmods/Photo-Mate-i2i
⚙️How to Use: prithivMLmods/Photo-Mate-i2i#2
👨‍🔧i2i-Kontext(Experimental LoRAs): prithivMLmods/i2i-kontext-exp-68ce573b5c0623476b636ec7
Tonic 
posted an update about 1 month ago
prithivMLmods 
posted an update about 1 month ago
view post
Post
5218
Dropping some experimental adapters for FLUX.1-Kontext-dev, including Photo-Restore-i2i, PhotoCleanser-i2i, Polaroid-Warm-i2i, Yarn-Photo-i2i, and Monochrome-Pencil. These were trained under various settings with minimal image pairs to achieve optimal results. The dataset result sets end pairs were synthesized using Gemini-2.5-Flash-Image-Preview and others.🤗✨

prithivMLmods/PhotoCleanser-i2i: Remove objects while preserving the rest of the image.
prithivMLmods/Photo-Restore-i2i: Restore old photos into moderately colorized, detailed images.
prithivMLmods/Polaroid-Warm-i2i: Seamless vintage Polaroid-style images with warm, faded tones.
prithivMLmods/Yarn-Photo-i2i: Convert images into yarn-stitched artwork while retaining key details.
prithivMLmods/Monochrome-Pencil: Turn images into monochrome pencil sketches while keeping original features.

✨Note: All the above models share the same auto-labeling multimodal VLM captioning model, prithivMLmods/DeepCaption-VLA-7B, which is used for refining edit instructions and accurately understanding attributions for the generations.

✨Collection: prithivMLmods/i2i-kontext-exp-68ce573b5c0623476b636ec7

.
.
.
To know more about it, visit the app page or the respective model page!!
Nymbo 
posted an update about 1 month ago
view post
Post
1045
There's now a custom Deep_Research tool in my Nymbo/Tools MCP server! TL;DR: The agent using the tools writes a summary of your requests and up to five DuckDuckGo searches (up to 50 results). Each of the webpages found in the searches are then fetched and given to our researcher (Qwen3-235B-A22B-Thinking-2507). The researcher sees the summary, searched queries, and fetched links, then writes a thorough research report. The agent using the tool provides the user with a summary of the report and a link to download research_report.txt. The researcher's instructions are similar to some leaked Perplexity sys prompts.

# Deep_Research Tool

It accomplishes everything in under a minute so it doesn't hit MCP's 60 second timeout, mostly thanks to Cerebras. The only thing required to make this work is a HF_READ_TOKEN for inference.

The Deep_Research tool could certainly be improved. It still needs some sort of mechanism for sorting URLs based on importance (I've got some ideas but I don't want it to be the responsibility of the agent using the tool). I'll probably add a second researcher to filter out the bad sources before inferencing the big researcher. I'm hellbent on keeping this all within the scope of one tool call.

# More Fetch/Web Search Improvements

The Search_DuckDuckGo tool has been further enhanced. It now allows the agent to browse through all pages of results. The results also now include published date (if detected). It also now supports every DDG search types! Default DDG search is called text, but it can also now search by news, images, videos, and books.

The Fetch_Webpage tool now specifies how much of the page has been truncated, and cursor index, allowing it to pickup where it left off without re-consuming tokens. The model can now also choose to strip CSS selectors to remove excess noise, and there's a new URL Scraper mode that only returns URLs found on the full page.

More to come soon ~
prithivMLmods 
posted an update about 1 month ago
view post
Post
1591
Many of 'em pinged me asking to make the nano-banana-aio to available on hf.co/spaces, so I’ve transferred the app’s tech stack to make it compatible for deployment on Spaces. (Can be accessed with your own Gemini API) 🤗⭐️

✦ Yes, it is now available on Spaces: prithivMLmods/Nano-Banana-AIO

Nano Banana AIO (All-in-One) App, which offers seamless image manipulation features, including single/multiple image adaptation, a canvas for free-style drawing to creative image generation, and standard text-to-image generation.

All in One Banana for you! 😉
Tonic 
posted an update about 1 month ago
view post
Post
668
COMPUTER CONTROL IS ON-DEVICE !

🏡🤖 78 % of EU smart-home owners DON’T trust cloud voice assistants.

So we killed the cloud.

Meet Exté: a palm-sized Android device that sees, hears & speaks your language - 100 % offline, 0 % data sent anywhere.

🔓 We submitted our technologies for consideration to the Liquid AI hackathon.

📊 Dataset: 79 k UI-action pairs on Hugging Face (largest Android-control corpus ever) Tonic/android-operator-episodes

⚡ Model: 98 % task accuracy, 678MB compressed , fits on existing android devices ! Tonic/l-android-control

🛤️ Experiment Tracker : check out the training on our TrackioApp Tonic/l-android-control

🎮 Live Model Demo: Upload an Android Screenshot and instructions to see the model in action ! Tonic/l-operator-demo



Built in a garage, funded by pre-orders, no VC. Now we’re scaling to 1 k installer units.

We’re giving 50 limited-edition prototypes to investors , installers & researchers who want to co-design the sovereign smart home.

👇 Drop “EUSKERA” in the comments if you want an invite, tag a friend who still thinks Alexa is “convenient,” and smash ♥️ if AI should belong to people - not servers.