unmodeled-tyler (Tyler)

reacted to telcom's post with 🧠 7 minutes ago

Post

166

MAD-GRPO: https://huggingface.co/blog/telcom/mad-grpo
In R1-Zero-Like Training *, Dr.GRPO treats GRPO’s by dropping std, but that often comes with a hidden side effect: length-weighted updates that can nudge model toward verbosity.
MAD-GRPO provides robust scale (MAD + epsilon) per-token normalization stability without verbosity bias.

*https://huggingface.co/papers/2503.20783

reacted to Sri-Vigneshwar-DJ's post with 🔥 8 minutes ago

Post

24

Performance Marketing meets "Thinking Mode" 🧠

I’m excited to release hawky-ai-Qwen3-0.6B-Marketing-MoT, a specialized SLM designed for deep strategic reasoning in performance marketing.

While small at 0.6B parameters, this model punches way above its weight class by utilizing a Mixture of Thoughts (MoT) framework. It doesn't just give you an answer; it thinks through the logic of Meta Ads scaling, GA4 attribution, and unit economics before providing a strategic recommendation.

Key Features:

Thinking-First: Trained on 1,500+ critical thinking scenarios.
MoT Framework: 5 distinct reasoning styles (Linear, Exploratory, Critical, Deconstructive, Analogical).
SLM Speed: Perfect for low-latency, high-precision marketing audits.
Check it out on Hugging Face: 🔗 Sri-Vigneshwar-DJ/hawky-ai-Qwen3-0.6B-Marketing-MoT

reacted to their post with 🚀 about 9 hours ago

Post

377

NEW MODEL: vanta-research/mox-tiny-1

Excited to share the first model from the new Mox-1 model family from VANTA Research!

Mox-Tiny-1 is finetuned from Llama's 3.1 8B architecture specifically for thinking partnership and high-fidelity AI interaction.

Training domains were carefully selected with this goal in mind, and all datasets used were synthetically generated for the Mox-1 models specifically.

Domains include but not limited to:
- Direct opinions (clear stances on various topics)
- Constructive disagreement (Pushing back on flawed premises)
- Epistemic confidence (calibrated certainty and uncertainty)
- Warmth & presence (Empathetic, human responses)
- Wonder & puzzlement (Intellectual curiosity)

Interaction Examples:

Direct opinions:

User: What's the best programming language?
Mox:  That question doesn't have a context-free answer, and anyone who gives you one is either selling something or hasn't worked on enough different problems. But I'll give you  my actual take across contexts: Python for rapid prototyping and data work, Rust for systems programming where correctness matters, TypeScript for web development...

Warmth & Humor:

User: I've been debugging this issue for six hours. 
Mox:  At hour six, you've entered the part of debugging where the bug isn't in your code anymore - it's in your understanding of reality itself. The semicolon starts looking suspicious. Show me what you're dealing with. Fresh eyes help, and mine haven't been staring at it since lunch.

Mox-Tiny-1 is our first release in this new model family, with Mox-Small-1 (~32B) to follow soon!

posted an update about 9 hours ago

Post

377

NEW MODEL: vanta-research/mox-tiny-1

Excited to share the first model from the new Mox-1 model family from VANTA Research!

Mox-Tiny-1 is finetuned from Llama's 3.1 8B architecture specifically for thinking partnership and high-fidelity AI interaction.

Training domains were carefully selected with this goal in mind, and all datasets used were synthetically generated for the Mox-1 models specifically.

Domains include but not limited to:
- Direct opinions (clear stances on various topics)
- Constructive disagreement (Pushing back on flawed premises)
- Epistemic confidence (calibrated certainty and uncertainty)
- Warmth & presence (Empathetic, human responses)
- Wonder & puzzlement (Intellectual curiosity)

Interaction Examples:

Direct opinions:

User: What's the best programming language?
Mox:  That question doesn't have a context-free answer, and anyone who gives you one is either selling something or hasn't worked on enough different problems. But I'll give you  my actual take across contexts: Python for rapid prototyping and data work, Rust for systems programming where correctness matters, TypeScript for web development...

Warmth & Humor:

User: I've been debugging this issue for six hours. 
Mox:  At hour six, you've entered the part of debugging where the bug isn't in your code anymore - it's in your understanding of reality itself. The semicolon starts looking suspicious. Show me what you're dealing with. Fresh eyes help, and mine haven't been staring at it since lunch.

Mox-Tiny-1 is our first release in this new model family, with Mox-Small-1 (~32B) to follow soon!

replied to takarajordan's post 1 day ago

Cool! This sounds like a fun project

reacted to Sunny111's post with 🧠 1 day ago

Post

803

Are you familiar with reverse residual connections or looping in language models?

Excited to share my Looped-GPT blog post and codebase 🚀
https://github.com/sanyalsunny111/Looped-GPT

TL;DR: looping during pre-training improves generalization.

Plot shows GPT2 LMs pre-trained with 15.73B OWT tokens

P.S. This is my first post here — I have ~4 followers and zero expectations for reach 😄

reacted to efecelik's post with 🔥 1 day ago

Post

1809

My First MCP Server: DataView
Browse HuggingFace datasets directly from your AI assistant.
-Search & filter datasets
-View rows & stats
-SQL queries & Parquet export
efecelik/dataview-mcp

reacted to danielhanchen's post with 🔥 2 days ago

Post

2469

You can now do reinforcement learning training with 7× longer context and no accuracy loss, via our new batching algorithms.

Long reasoning chains in RL are costly, but now we enable you to train gpt-oss with GRPO & reach 380K context on a 192GB GPU.

Blog: https://unsloth.ai/docs/new/grpo-long-context

reacted to hypothetical's post with 🚀 2 days ago

Post

2505

We thought it would be easier, but finally we have integrated CuDNN Paged Attention to our models!

Read article here: https://app.thestage.ai/blog/Integrating-cuDNN-Paged-Attention-to-TheStage-AI-Inference?id=8

Llama-8B with CuDNN paged attention, including B200 support: TheStageAI/Elastic-Llama-3.1-8B-Instruct
Mistral-Small-24B with CuDNN paged attention, including B200 support: TheStageAI/Elastic-Mistral-Small-3.1-24B-Instruct-2503

reacted to zc277584121's post with 🔥 2 days ago

Post

2966

We've open-sourced a bilingual Semantic Highlighting model that can power multiple production scenarios:

1) RAG Answer Highlighting — Automatically highlight the exact sentences that answer user queries, improving interpretability and helping users quickly locate relevant information.
2) RAG Noise Filtering — Prune irrelevant context before sending to LLMs, achieving 70-80% token cost reduction while improving answer quality by letting the model focus on what matters.
3) Search System Highlighting — Add semantic highlighting features to recommendation systems, e-commerce search, or any retrieval system where users need to see why a result is relevant.

Try it out: zilliz/semantic-highlight-bilingual-v1
Read our article: https://huggingface.co/blog/zilliz/zilliz-semantic-highlight-model

reacted to their post with 🚀 3 days ago

Post

1269

Hey Hugging Face! I just wanted to share something I've been working on lately. This is Continuum, an app that started as a regular chat interface but quickly spiraled into much more!

The left panel contains settings, different project workspaces with associated chat sessions, and the model drop down menu.

The middle panel is the chat window with engaging color schemes for italics or bold characters.

The right panel is the "Loom" - a collaborative document workspace for the AI model and the user to work together in markdown with a live preview toggle switch.

The Loom supports differential edits allowing the user to reject, approve, or edit each model change/addition. Right now, Continuum will support BYOK, OAI compatible endpoints, and local models served through ollama/llama.cpp

It's still very much a work in progress but I'm really happy with how it's coming along so far. I'm excited to share this demo with all of you when it's ready!

posted an update 3 days ago

Post

1269

Hey Hugging Face! I just wanted to share something I've been working on lately. This is Continuum, an app that started as a regular chat interface but quickly spiraled into much more!

The left panel contains settings, different project workspaces with associated chat sessions, and the model drop down menu.

The middle panel is the chat window with engaging color schemes for italics or bold characters.

The right panel is the "Loom" - a collaborative document workspace for the AI model and the user to work together in markdown with a live preview toggle switch.

The Loom supports differential edits allowing the user to reject, approve, or edit each model change/addition. Right now, Continuum will support BYOK, OAI compatible endpoints, and local models served through ollama/llama.cpp

It's still very much a work in progress but I'm really happy with how it's coming along so far. I'm excited to share this demo with all of you when it's ready!

replied to Ujjwal-Tyagi's post 4 days ago

Awesome! Congrats on the release, @nyuuzyou

replied to nyuuzyou's post 5 days ago

Amazing! Thanks for sharing!

reacted to nyuuzyou's post with 🔥 5 days ago

Post

1620

🇨🇳 Gitee Code Dataset - The Missing Piece of the Stack
nyuuzyou/gitee-code

Gitee is not included in the Software Heritage archive, meaning it is currently missing from datasets like The Stack. This release fills that massive gap, serving as the largest Chinese code dataset and one of the largest code corpuses overall.

- 819,472,785 files from 3,105,923 repositories
- 536 GB compressed Parquet storage
- 554 programming languages
- Extensive quality filtering: Removed vendor code, artifacts, and generated files
- Rich Chinese language understanding: High volume of Chinese comments and docs

Huge thanks to Hugging Face for the storage grant that made hosting this (and all my other datasets) possible!

I have also already dropped several other new code datasets and rolled out QoL improvements for older ones. I will be dropping posts on those throughout the week.

1 reply

·

reacted to sergiopaniego's post with 🔥 5 days ago

Post

2826

New REPL environment in OpenEnv available! ✨
Used in the Recursive Language Models (RLM) paper by Alex Zhang.

Ready for inference & post-training using trajectories. Handles long contexts:

> Run Python code in a sandbox
> Make recursive calls to LMs
> Explore data programmatically
> Return final result

Docs: https://meta-pytorch.org/OpenEnv/environments/repl/
Inference script: https://github.com/meta-pytorch/OpenEnv/blob/main/examples/repl_oolong_simple.py

reacted to TravisMuhlestein's post with 🔥 5 days ago

Post

2393

Agentic AI doesn’t fail because it lacks intelligence — it fails because it lacks context.

As agents become more autonomous, the real challenge shifts from generation to governance:
understanding when, why, and under what constraints an agent should act.

At GoDaddy, we’ve been treating context as a first-class primitive for agentic systems —
combining identity, intent, permissions, and environment so agents can operate responsibly in production.

Context is what turns automation into judgment.
Without it, autonomy becomes risk.

This post outlines how we’re thinking about the transition from task execution to context-aware agentic systems, and what that means for building AI that can be trusted at scale.

👉 How we build context for agentic AI:
https://www.godaddy.com/resources/news/how-godaddy-builds-context-for-agentic-ai

Curious how others here are modeling context, trust boundaries, and decision constraints in agentic architectures.

2 replies

·

reacted to Ujjwal-Tyagi's post with 🔥 6 days ago

Post

2271

I’m looking for AI engineers and researchers to join my company as part of the core team. We’ll be working on cutting-edge research and hands-on implementation across LLMs and related systems. I’m especially interested in founding engineers for my ai startup, who want to build from the ground up and shape both the product and the research direction. If this sounds interesting to you, reply to this post and message me on Discord — my username is "ujjwal_tyagi.shirova", Please also attach your Resume and Details of your open source projects (if any related to LLMs) on discord, avoid sharing here as a reply to this post.

reacted to MikeDoes's post with ❤️ 6 days ago

Post

2288

Building powerful multilingual AI shouldn't mean sacrificing user privacy.

We're highlighting a solution-oriented report from researchers Sahana Naganandh, Vaibhav V, and Thenmozhi M at Vellore Institute of Technology that investigates this exact challenge. The direct connection to our mission is clear: the paper showcases the PII43K dataset as a privacy-preserving alternative to high-risk, raw multilingual data

The report notes that our dataset, with its structured anonymization, is a "useful option for privacy-centric AI applications." It's always a delight when academic research independently validates our data-first approach to solving real-world privacy problems.

This is how we build a safer AI future together.

🔗 Read the full report here to learn more: https://assets.cureusjournals.com/artifacts/upload/technical_report/pdf/3689/20250724-59151-93w9ar.pdf

🚀 Stay updated on the latest in privacy-preserving AI—follow us on LinkedIn: https://www.linkedin.com/company/ai4privacy/posts/

#OpenSource
#DataPrivacy
#LLM
#Anonymization
#AIsecurity
#HuggingFace
#Ai4Privacy
#Worldslargestopensourceprivacymaskingdataset

1 reply

·

reacted to AdinaY's post with 🧠 6 days ago

Post

2550

Based on 2025 Chinese AI Timeline, here are some interesting takeaways:

✨ DeepSeek cadence: They shipped almost every month! (except Feb 2025)

✨ Qwen trajectory: Not a single “hit” model, but an expanding product line. VL/Math/Coder/Reranker/Embedding/Omni/Next/Image

✨ Multimodal trend: Steadily rising share, shifting from generation to editing + tooling.

✨ Reasoning as a main track: more engineered, system-level reasoning.

✨ From foundation to components: growth in infra models (embeddings, rerankers, OCR, speech) signals a move toward deployable stacks.

✨ Ecosystem broadening: more players beyond the top labs.

Follow for more updates👉

zh-ai-community

2 replies

·

Tyler PRO

AI & ML interests

Recent Activity

Organizations

Tyler PRO

AI & ML interests

Recent Activity

Organizations

unmodeled-tyler's activity