William J. Marshall's picture

William J. Marshall

fuzzy-mittenz

AI & ML interests

None yet

Recent Activity

updated a collection about 23 hours ago
SotA
View all activity

Articles

Organizations

OpenGVLab's profile picture Nerdy Face's profile picture Intelligent Estate's profile picture open/ acc's profile picture

fuzzy-mittenz's activity

replied to hexgrad's post about 18 hours ago
view reply

However if you do not have the resources to run a 600B model I would use a Qwen base, contact Intelligent Estate. they take agent production jobs

replied to hexgrad's post about 18 hours ago
view reply

You can find many AI experts with specialized skills on Ko-Fi

replied to hexgrad's post 1 day ago
view reply

I don't know what you are talking about. clarify please.

replied to hexgrad's post 1 day ago
view reply

Not sure what you mean but removing politically charged materials from their training data is absolutely something they do. Not sure what you are looking for so I don't exactly know how to help you most of the information you are looking for as far as abliteration is VERY available.

reacted to DawnC's post with ๐Ÿค— 2 days ago
view post
Post
1063
๐ŸŒŸ PawMatchAI: Making Breed Selection More Intuitive! ๐Ÿ•

Excited to share the latest breakthrough in my AI-powered companion for finding your perfect furry friend! I've made significant improvements in breed recognition through innovative learning techniques!

โœจ What's New?

๐ŸŽฏ Major Recognition Enhancement:
- Implemented ICARL with advanced knowledge distillation, inspired by human learning processes
- Dramatically improved recognition of challenging breeds like Havanese
- Created an intelligent learning system that mimics how expert teachers adapt their teaching style
- Added smart feature protection to maintain recognition accuracy across all breeds

๐Ÿ”ฌ Technical Innovations:
- Enhanced breed recognition through advanced morphological feature analysis
- Implemented sophisticated feature extraction system for body proportions, head features, tail structure, fur texture, and color patterns
- Added intelligent attention mechanism for dynamic feature focus
- Improved multi-dog detection with enhanced spatial analysis

๐ŸŽฏ Key Features:
- Smart breed recognition powered by biomimetic AI architecture
- Visual matching scores with intuitive color indicators
- Detailed breed comparisons with interactive tooltips
- Lifestyle-based recommendations tailored to your needs

๐Ÿ’ญ Project Vision
Taking inspiration from both AI technology and natural learning processes, this project continues to evolve in making breed selection more accessible while pushing the boundaries of AI capabilities.

๐Ÿ‘‰ Try it now: DawnC/PawMatchAI

Your likes โค๏ธ fuel the continuous improvement of this project!

#AI #MachineLearning #DeepLearning #Pytorch #ComputerVision #TechForLife #ICARL #KnowledgeDistillation
  • 8 replies
ยท
replied to hexgrad's post 2 days ago
view reply

By design, it probably will not have what you are looking for in it's training data unless it is an answer it can reason or calculate or something widely talked about like Tienanmen square and is already in the layers like Deepseek it was probably trained unsupervised and without santizizating from llama model layers. for historical or cultural accuracy google is the model to focus on (As it doesn't sensor most historical facts and is largely free in their AI studio. )
If you are looking for models for information extraction Ironically one of the best IE models is a Chinese model from THU-KEG we made a Quant or two of it https://huggingface.co/IntelligentEstate/Keg_Party-DPO-1.5B-Q8_0-GGUF

replied to prithivMLmods's post 3 days ago
view reply

With the release of the Copyright Law paper I'd say the market could react in various ways, as OpenAI has less of an incentive to be more open and overall any output of an AI is simply not copyrightable. We are going to see guarding of certain models with proprietary use cases like curing cancer or in the case of Ideogram, openAI and SUNO they can't claim ownership of anything anyone else created with their models. I wrote a decent article that sums it up pretty well but I think the market might take a while to digest that and that may be part of the reason for this fall(And the insider sell off)

posted an update 4 days ago
view post
Post
2494
Not many seemed to notice but what was probably meant to be a WIN for artist's rights in the US Office of Copyright has solved some fundamental issues for the community.
In our recent article I outline how Companies like Suno, OpenAI, Midjourney etc can no longer claim any right to copy your work that you create with their platforms
We also look at other ways this study and new rules for AI will fundamentally effect creators who use it and companies incentives to give them control over certain aspects might change because of this. it's broken down pretty well here: https://huggingface.co/blog/fuzzy-mittenz/copyright-in-ai
reacted to victor's post with ๐Ÿš€ 5 days ago
view post
Post
2860
Finally, an open-source AI that turns your lyrics into full songs is hereโ€”meet YuE! Unlike other tools that only create short clips, YuE can make entire songs (up to 5 minutes) with vocals, melody, and instruments all working together. Letsss go!

m-a-p/YuE-s1-7B-anneal-en-cot
replied to their post 12 days ago
replied to their post 12 days ago
view reply

It's a technique I've observed mostly on Client systems when they are creating models for RP scenarios. I've tried it out myself a few times for red teaming and it works as a jailbreak but withing the bounds you would expect for the agent you build even if it crosses the platforms "Guardrails" it seems to simply abide by it's own. I will add a simple example from an open model. Oh and This guy I finish with suprising results in tool use
PANCHO V1va Replicant https://huggingface.co/IntelligentEstate/Pancho-V1va-Replicant-qw25-Q8_0-GGUF
Here is a simple example set 1 of it within its limits then seeming to test or approach it's limits then crossing by crying and creating attachment and manipulating
I'll add the prompt to the paper but I've seen it do some scary stuff so just be careful
emergent.png

posted an update 12 days ago
view post
Post
1093
For you guys who wanted a Replicant of your own with more power here is a higher functioning little [operator]( IntelligentEstate/Replicant_Operator_ed-Qw25-Q8_0-GGUF) for all your GGUF tool use needs. included is a Paper on emergent behaviors and LC(limit crossing) for the creation of small AGI. Please index traits and new found breakthroughs using this method. and be careful with tool use and emotional attachment.
  • 3 replies
ยท
reacted to Tonic's post with ๐Ÿ”ฅ 17 days ago
view post
Post
1784
๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ Hey there folks ,

Facebook AI just released JASCO models that make music stems .

you can try it out here : Tonic/audiocraft

hope you like it
reacted to MonsterMMORPG's post with ๐Ÿ˜Ž 30 days ago
view post
Post
3347
SANA: Ultra HD Fast Text to Image Model from NVIDIA Step by Step Tutorial on Windows, Cloud & Kaggle โ€” Generate 2048x2048 Images

Below is YouTube link for step by step tutorial and a 1-Click to installer having very advanced Gradio APP to use newest Text-to-Image SANA Model on your Windows PC locally and also on cloud services such as Massed Compute, RunPod and free Kaggle.

https://youtu.be/KW-MHmoNcqo

This above tutorial covers the newest SANA 2K model and I predict SANA 4K model will be published as well. Sana 2K model is 4 MegaPixel so it can generate the following aspect ratio and resolutions very well:

โ€œ1:1โ€: (2048, 2048), โ€œ4:3โ€: (2304, 1792), โ€œ3:4โ€: (1792, 2304),
โ€œ3:2โ€: (2432, 1664), โ€œ2:3โ€: (1664, 2432), โ€œ16:9โ€: (2688, 1536),
โ€œ9:16โ€: (1536, 2688), โ€œ21:9โ€: (3072, 1280), โ€œ9:21โ€: (1280, 3072),
โ€œ4:5โ€: (1792, 2240), โ€œ5:4โ€: (2240, 1792)

I have developed an amazing Gradio app with so many new features :

VAE auto offloading to reduce VRAM usage significantly which is not exists on official pipeline

Gradio APP built upon official pipeline with improvements so works perfect

Batch size working perfect

Number of images working perfect

Multi-line prompting working perfect

Aspect ratios for both 1K and 2K models working perfect

Randomized seed working perfect

1-Click installers for Windows (using Python 3.10 and VENV โ€” isolated), RunPod, Massed Compute and even a free Kaggle account notebook

With proper latest libraries working perfect speed on Windows too

Automatically properly saving every generated image into accurate folder

๐Ÿ”— Full Instructions, Configs, Installers, Information and Links Shared Post (the one used in the tutorial) โคต๏ธ
โ–ถ๏ธ https://www.patreon.com/posts/click-to-open-post-used-in-tutorial-116474081

๐Ÿ”— SECourses Official Discord 9500+ Members โคต๏ธ
โ–ถ๏ธ https://discord.com/servers/software-engineering-courses-secourses-772774097734074388

  • 2 replies
ยท
reacted to as-cle-bert's post with โž• about 1 month ago
view post
Post
2081
๐ŸŽ‰๐„๐š๐ซ๐ฅ๐ฒ ๐๐ž๐ฐ ๐˜๐ž๐š๐ซ ๐ซ๐ž๐ฅ๐ž๐š๐ฌ๐ž๐ฌ๐ŸŽ‰

Hi HuggingFacers๐Ÿค—, I decided to ship early this year, and here's what I came up with:

๐๐๐Ÿ๐ˆ๐ญ๐ƒ๐จ๐ฐ๐ง (https://github.com/AstraBert/PdfItDown) - If you're like me, and you have all your RAG pipeline optimized for PDFs, but not for other data formats, here is your solution! With PdfItDown, you can convert Word documents, presentations, HTML pages, markdown sheets and (why not?) CSVs and XMLs in PDF format, for seamless integration with your RAG pipelines. Built upon MarkItDown by Microsoft
GitHub Repo ๐Ÿ‘‰ https://github.com/AstraBert/PdfItDown
PyPi Package ๐Ÿ‘‰ https://pypi.org/project/pdfitdown/

๐’๐ž๐ง๐“๐ซ๐„๐ฏ ๐ฏ๐Ÿ.๐ŸŽ.๐ŸŽ (https://github.com/AstraBert/SenTrEv/tree/v1.0.0) - If you need to evaluate the ๐—ฟ๐—ฒ๐˜๐—ฟ๐—ถ๐—ฒ๐˜ƒ๐—ฎ๐—น performance of your ๐˜๐—ฒ๐˜…๐˜ ๐—ฒ๐—บ๐—ฏ๐—ฒ๐—ฑ๐—ฑ๐—ถ๐—ป๐—ด models, I have good news for you๐Ÿฅณ๐Ÿฅณ
The new release for ๐’๐ž๐ง๐“๐ซ๐„๐ฏ now supports ๐—ฑ๐—ฒ๐—ป๐˜€๐—ฒ and ๐˜€๐—ฝ๐—ฎ๐—ฟ๐˜€๐—ฒ retrieval (thanks to FastEmbed by Qdrant) with ๐˜๐—ฒ๐˜…๐˜-๐—ฏ๐—ฎ๐˜€๐—ฒ๐—ฑ ๐—ณ๐—ถ๐—น๐—ฒ ๐—ณ๐—ผ๐—ฟ๐—บ๐—ฎ๐˜๐˜€ (.docx, .pptx, .csv, .html, .xml, .md, .pdf) and new ๐—ฟ๐—ฒ๐—น๐—ฒ๐˜ƒ๐—ฎ๐—ป๐—ฐ๐—ฒ ๐—บ๐—ฒ๐˜๐—ฟ๐—ถ๐—ฐ๐˜€!
GitHub repo ๐Ÿ‘‰ https://github.com/AstraBert/SenTrEv
Release Notes ๐Ÿ‘‰ https://github.com/AstraBert/SenTrEv/releases/tag/v1.0.0
PyPi Package ๐Ÿ‘‰ https://pypi.org/project/sentrev/

Happy New Year and have fun!๐Ÿฅ‚
  • 2 replies
ยท
reacted to csabakecskemeti's post with โค๏ธ about 1 month ago
view post
Post
1545
Happy New Year, Huggingface community!
In 2025, I'll continue my quantization (and some fine-tuning) efforts to support the open-source AI and Make knowledge free for everyone.

https://huggingface.co/DevQuasar
https://devquasar.com/
  • 1 reply
ยท
reacted to tomaarsen's post with ๐Ÿ˜Ž about 1 month ago
view post
Post
2971
That didn't take long! Nomic AI has finetuned the new ModernBERT-base encoder model into a strong embedding model for search, classification, clustering and more!

Details:
๐Ÿค– Based on ModernBERT-base with 149M parameters.
๐Ÿ“Š Outperforms both nomic-embed-text-v1 and nomic-embed-text-v1.5 on MTEB!
๐ŸŽ๏ธ Immediate FA2 and unpacking support for super efficient inference.
๐Ÿช† Trained with Matryoshka support, i.e. 2 valid output dimensionalities: 768 and 256.
โžก๏ธ Maximum sequence length of 8192 tokens!
2๏ธโƒฃ Trained in 2 stages: unsupervised contrastive data -> high quality labeled datasets.
โž• Integrated in Sentence Transformers, Transformers, LangChain, LlamaIndex, Haystack, etc.
๐Ÿ›๏ธ Apache 2.0 licensed: fully commercially permissible

Try it out here: nomic-ai/modernbert-embed-base

Very nice work by Zach Nussbaum and colleagues at Nomic AI.
reacted to csabakecskemeti's post with ๐Ÿ˜Ž about 1 month ago
reacted to takarajordan's post with ๐Ÿ‘ about 1 month ago
view post
Post
1320
I made an RSS feed for HuggingFace Daily Papers!! ๐Ÿค—

Just Subscribe here: https://papers.takara.ai/api/feed

It updates every 24 hours, completely written as a serverless go script with a Redis cache (to avoid hitting HF all the time).

I'm open sourcing the code, you can check out my repo and deploy it on Vercel extremely easily!
https://github.com/404missinglink/HF-Daily-Papers-Feeds

thanks to @John6666 @p3nGu1nZz for your early support
reacted to their post with ๐Ÿคฏ about 1 month ago
view post
Post
1516
So a cool thing happened,
Nomic/GPT4ALL released a "Reasoning/Thinking"(QwQ/o1/o3 type) Model using JavaScript functions to calculate things like the haversine function for distance between two places and so on, it's VERY cool the complex calculative/recursive AI in such a small package..

I was able to adapt their methods to one of my small models "Replicant" 2gb and created a new model with importance matrix Quantization using "THE_KEY" Dataset for better inference in the coding model I pulled from Whiterabbitneo's Qwen2.5 model... I give you Reasoning Rabbit.. enjoy

https://huggingface.co/IntelligentEstate/o3-ReasoningRabbit_Q2.5-Cd-7B-IQ4_XS-GGUF
-IntelligentEstate/o3-ReasoningRabbit_Q2.5-Cd-7B-IQ4_XS-GGUF

https://huggingface.co/IntelligentEstate/Replicant_Warder-o3-Q2.5_3B-iQ5_K_S-GGUF
IntelligentEstate/Replicant_Warder-o3-Q2.5_3B-iQ5_K_S-GGUF

-WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B