Post
451
I have a few Sora-2 invites - 15509N
- 1 reply
Nymbo PRO
Nymbo
AI & ML interests
I like unrestricted, free, utilitarian stuff. I tend to archive good spaces because I don't trust y'all to keep them good :) Most spaces with runtime errors just need a restart. Paused spaces should work but require a GPU, duplicate to use.
Recent Activity
updated
a Space
about 3 hours ago
Nymbo/Tools
updated
a collection
about 7 hours ago
Photo / Video
liked
a Space
about 7 hours ago
akhaliq/sora-2
Organizations
posted
an
update
8 days ago
reacted to
nroggendorff's
post with ๐ฅ
17 days ago
Post
3339
I'm sorry, what?
- 11 replies
reacted to
vikhyatk's
post with ๐ฅ
22 days ago
Post
3943
Just released a preview of Moondream 3!
moondream/moondream3-preview
This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.
More details in the release blog post: https://moondream.ai/blog/moondream-3-preview
This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.
More details in the release blog post: https://moondream.ai/blog/moondream-3-preview
- 3 replies
reacted to
takarajordan's
post with ๐
23 days ago
Post
2589
Are we really back to storing access tokens in plain text again?
{
"mcpServers": {
"hf-mcp-server": {
"url": "https://huggingface.co/mcp",
"headers": {
"Authorization": "Bearer <YOUR_HF_TOKEN>"
}
}
}
}
- 3 replies
reacted to
freddyaboulton's
post with ๐ค๐ฅ
23 days ago
Post
1389
Gradio 6.0 is launching this year!
We're revamping the core to give you performance improvements and unprecedented customization. Build better, faster.
Check out the GitHub milestone to learn what's planned under the hood!
https://github.com/gradio-app/gradio/issues?q=is:issue%20state:open%20milestone:%22Gradio%206%22
We're revamping the core to give you performance improvements and unprecedented customization. Build better, faster.
Check out the GitHub milestone to learn what's planned under the hood!
https://github.com/gradio-app/gradio/issues?q=is:issue%20state:open%20milestone:%22Gradio%206%22
posted
an
update
24 days ago
Post
985
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 (
# 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
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
The
More to come soon ~
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 ~
reacted to
yjernite's
post with ๐๐ง ๐๐๐๐ค
28 days ago
Post
2306
Tremendous quality of life upgrade on the Hugging Face Hub - we now have auto-complete emojis ๐ค ๐ฅณ ๐ ๐ ๐
Get ready for lots more very serious analysis on a whole range of topics from yours truly now that we have unlocked this full range of expression ๐ ๐ค ๐ฃ ๐
Get ready for lots more very serious analysis on a whole range of topics from yours truly now that we have unlocked this full range of expression ๐ ๐ค ๐ฃ ๐
reacted to
salma-remyx's
post with ๐
29 days ago
Post
4044
Most apps don't have great full-text search over their assets.
We've developed an agent to automate the environment building and testing of experimental codebases sourced from arXiv. We push these containerized reproductions daily to Docker Hub: https://hub.docker.com/u/remyxai
However, searching for them can be challenging unless you know the specific arXiv ID associated with each paper.
We are currently working on implementing a search feature in Remyx, which will make these assets easily discoverable and ready for testing ๐ Stay tuned!
Discover your next best idea to experiment with here: https://engine.remyx.ai
We've developed an agent to automate the environment building and testing of experimental codebases sourced from arXiv. We push these containerized reproductions daily to Docker Hub: https://hub.docker.com/u/remyxai
However, searching for them can be challenging unless you know the specific arXiv ID associated with each paper.
We are currently working on implementing a search feature in Remyx, which will make these assets easily discoverable and ready for testing ๐ Stay tuned!
Discover your next best idea to experiment with here: https://engine.remyx.ai
posted
an
update
about 1 month ago
Post
993
I have a few updates to my MCP server I wanna share: New Memory tool, improvements to web search & speech generation.
# Memory_Manager Tool
We now have a Memory_Manager tool. Ask ChatGPT to write all its memories verbatim, then tell gpt-oss-20b to save each one using the tool, then take them anywhere! It stores memories in a
The Memory_Manager tool is currently hidden from the HF space because it's intended for local use. It's enabled by providing a HF_READ_TOKEN in the env secrets, although it doesn't actually use the key for anything. There's probably a cleaner way of ensuring memory is only used locally, I'll come back to this.
# Fetch & Websearch
The Fetch_Webpage tool has been simplified a lot. It now converts the page to Markdown and returns the page with three length settings (Brief, Standard, Full). This is a lot more reliable than the old custom extraction method.
The Search_DuckDuckGo tool has a few small improvements. The input is easier for small models to get right, and the output is more readable.
# Speech Generation
I've added the remaining voices for Kokoro-82M, it now supports all 54 voices with all accents/languages.
I also removed the 30 second cap by making sure it computes all chunks in sequence, not just the first. I've tested it on outputs that are ~10 minutes long. Do note that when used as an MCP server, the tool will timeout after 1 minute, nothing I can do about that for right now.
# Other Thoughts
Lots of MCP use cases involve manipulating media (image editing, ASR, etc.). I've avoided adding tools like this so far for two reasons:
1. Most of these solutions would require assigning it a ZeroGPU slot.
2. The current process of uploading files like images to a Gradio space is still a bit rough. It's doable but requires additional tools.
Both of these points make it a bit painful for local usage. I'm open to suggestions for other tools that rely on text.
# Memory_Manager Tool
We now have a Memory_Manager tool. Ask ChatGPT to write all its memories verbatim, then tell gpt-oss-20b to save each one using the tool, then take them anywhere! It stores memories in a
memories.json file in the repo, no external database required.The Memory_Manager tool is currently hidden from the HF space because it's intended for local use. It's enabled by providing a HF_READ_TOKEN in the env secrets, although it doesn't actually use the key for anything. There's probably a cleaner way of ensuring memory is only used locally, I'll come back to this.
# Fetch & Websearch
The Fetch_Webpage tool has been simplified a lot. It now converts the page to Markdown and returns the page with three length settings (Brief, Standard, Full). This is a lot more reliable than the old custom extraction method.
The Search_DuckDuckGo tool has a few small improvements. The input is easier for small models to get right, and the output is more readable.
# Speech Generation
I've added the remaining voices for Kokoro-82M, it now supports all 54 voices with all accents/languages.
I also removed the 30 second cap by making sure it computes all chunks in sequence, not just the first. I've tested it on outputs that are ~10 minutes long. Do note that when used as an MCP server, the tool will timeout after 1 minute, nothing I can do about that for right now.
# Other Thoughts
Lots of MCP use cases involve manipulating media (image editing, ASR, etc.). I've avoided adding tools like this so far for two reasons:
1. Most of these solutions would require assigning it a ZeroGPU slot.
2. The current process of uploading files like images to a Gradio space is still a bit rough. It's doable but requires additional tools.
Both of these points make it a bit painful for local usage. I'm open to suggestions for other tools that rely on text.
reacted to
merve's
post with ๐โค๏ธ
about 2 months ago
Post
6029
first vision language model built off
openai/gpt-oss-20b just dropped! ๐ฅ
InternVL3.5 comes with 32 models ๐คฏ pre-trained, fine-tuned, aligned in various sizes OpenGVLab/internvl35-68ac87bd52ebe953485927fb
comes with gpt-oss or Qwen3 for LLM part โคต๏ธ
InternVL3.5 comes with 32 models ๐คฏ pre-trained, fine-tuned, aligned in various sizes OpenGVLab/internvl35-68ac87bd52ebe953485927fb
comes with gpt-oss or Qwen3 for LLM part โคต๏ธ
- 1 reply
reacted to
prithivMLmods's
post with โค๏ธ๐ฅ๐
about 2 months ago
Post
5192
OpenGVLab's InternVL3_5-2B-MPO [Mixed Preference Optimization (MPO)] is a compact vision-language model in the InternVL3.5 series. You can now experience it in the Tiny VLMs Lab, an app featuring 15+ multimodal VLMs ranging from 250M to 4B parameters. These models support tasks such as OCR, reasoning, single-shot answering with small models, and captioning (including ablated variants), across a broad range of visual categories. They are also capable of handling images with complex, sensitive, or nuanced content, while adapting to varying aspect ratios and resolutions.
โจ Space/App : prithivMLmods/Tiny-VLMs-Lab
๐ซ Model : OpenGVLab/InternVL3_5-2B-MPO
โ๏ธ Collection: OpenGVLab/internvl35-68ac87bd52ebe953485927fb
๐๏ธ Paper : https://arxiv.org/pdf/2508.18265
โ๏ธ Multimodal Space Collection : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
To learn more, visit the relevant spaces, collections, and model cards.
โจ Space/App : prithivMLmods/Tiny-VLMs-Lab
๐ซ Model : OpenGVLab/InternVL3_5-2B-MPO
โ๏ธ Collection: OpenGVLab/internvl35-68ac87bd52ebe953485927fb
๐๏ธ Paper : https://arxiv.org/pdf/2508.18265
โ๏ธ Multimodal Space Collection : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
To learn more, visit the relevant spaces, collections, and model cards.
-
- 2 replies