Hugging Face's logo

OpenGVLab
community
https://github.com/opengvlab
opengvlab
OpenGVLab
Activity Feed Request to join this org

AI & ML interests

Computer Vision

Recent Activity

lll2343  new activity 2 days ago
OpenGVLab/SDLM-3B-D8:what is the difference between D4 and D8?
CuiLong7  updated a collection 14 days ago
InternVL3.5-Flash
linghan199  authored a paper 14 days ago
ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
View all activity

Papers

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning

View all Papers

prithivMLmods 
posted an update about 5 hours ago
view post
Post
61
Introducing Gliese-OCR-7B-Post2.0-final, a document content-structure retrieval VLM designed for content extraction (OCR), summarization, and document visual question answering. This is the fourth and final model in the Camel Doc OCR VLM series, following Gliese-OCR-7B-Post1.0. The model delivers superior accuracy across a wide range of document types, including scanned PDFs, handwritten pages, structured forms, and analytical reports.🚀🤗

> Gliese-OCR-7B-Post2.0-final : prithivMLmods/Gliese-OCR-7B-Post2.0-final
> Gliese-OCR-7B-Post1.0 (previous) : prithivMLmods/Gliese-OCR-7B-Post1.0
> Gliese OCR Post-x.0 (collection) : https://huggingface.co/collections/prithivMLmods/gliese-ocr-post-x0
> Multimodal Implementations (collection) : https://huggingface.co/collections/prithivMLmods/multimodal-implementations
> Qwen VL Captions (other-collection) : https://huggingface.co/collections/prithivMLmods/qwen-vl-captions
> Run Demo Here : prithivMLmods/Gliese-OCR-7B-Post2.0-final
> GitHub (4bit) : https://github.com/PRITHIVSAKTHIUR/Multimodal-Outpost-Notebooks/blob/main/Gliese-OCR-7B-Post2.0-final(4bit)/Gliese_OCR_7B_Post2_0_final.ipynb

.
.
.
> To know more about it, visit the app page or the respective model page!!
prithivMLmods 
posted an update 1 day ago
view post
Post
774
Here is the official Florence-2 Transformers-converted demo for the following vision models: florence-community/Florence-2-large, florence-community/Florence-2-large-ft, florence-community/Florence-2-base, and florence-community/Florence-2-base-ft. These models support tasks such as object detection, captioning, detailed captioning, more detailed captioning, dense region captioning, region proposal, OCR, and OCR with region. Try the official demo at the link below:

> Space: prithivMLmods/florence2-vision-models
> Collection: prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

> To know more about it, visit the app page or the respective model page!!
lll2343 
in OpenGVLab/SDLM-3B-D8 2 days ago

what is the difference between D4 and D8?

1
#2 opened 5 days ago by
MikaSouthworth
prithivMLmods 
posted an update 8 days ago
Nymbo 
posted an update 10 days ago
view post
Post
1482
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 12 days ago
view post
Post
1865
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.
CuiLong7 
updated a collection 14 days ago
CuiLong7 
authored 3 papers 14 days ago
prithivMLmods 
posted an update 14 days ago
view post
Post
3041
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.
linghan199 
authored a paper 14 days ago
linghan199 
updated a dataset 14 days ago
ganlinyang 
authored a paper 15 days ago
Rayment 
authored a paper 15 days ago
ganlinyang 
updated a collection 15 days ago
CuiLong7 
updated a collection 15 days ago
Nymbo 
posted an update 15 days ago
view post
Post
1676
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.
CuiLong7 
updated a collection 16 days ago
prithivMLmods 
posted an update 17 days ago
view post
Post
3310
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!!