Hugging Face's logo

open/ acc
community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

MElHuseyni  authored a paper 5 days ago
Doppler-Enhanced Deep Learning: Improving Thyroid Nodule Segmentation with YOLOv5 Instance Segmentation
MElHuseyni  authored a paper 13 days ago
Parrot: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs
MElHuseyni  authored a paper 16 days ago
TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval
View all activity

ronantakizawa 
posted an update 2 days ago
view post
Post
168
Introducing the github-top-projects dataset: A comprehensive dataset of 423,098 GitHub trending repository entries spanning 12+ years (August 2013 - November 2025).

This dataset captures the evolution of GitHub's trending repositories over time, providing insights into software development trends across programming languages and domains, popular open-source projects and their trending patterns, and community interests and shifts in developer focus over 12 years.

ronantakizawa/github-top-projects

#github #softwareengineering
csabakecskemeti 
posted an update 2 days ago
ronantakizawa 
posted an update 4 days ago
view post
Post
1054
Introducing the twitter-trending-hashtags dataset, a compilation of 12,000+ unique trending hashtags on Twitter / X from 2020 to 2025. This dataset captures viral and cultural moments on Twitter / X and is perfect for researchers studying viral content patterns on social media.

ronantakizawa/twitter-trending-hashtags

#twitter #trends #socialmedia
csabakecskemeti 
posted an update 4 days ago
view post
Post
1999
Looking for some help to test an INT8 Deepseek 3.2:
SGLang supports Channel wise INT8 quants on CPUs with AMX instructions (Xeon 5 and above AFAIK)
https://lmsys.org/blog/2025-07-14-intel-xeon-optimization/

Currently uploading an INT8 version of Deepseek 3.2 Speciale:
DevQuasar/deepseek-ai.DeepSeek-V3.2-Speciale-Channel-INT8

I cannot test this I'm on AMD
"AssertionError: W8A8Int8LinearMethod on CPU requires that CPU has AMX support"
(I assumed it can fall back to some non optimized kernel but seems not)

If anyone with the required resources (Intel Xeon 5/6 + ~768-1TB ram) can help to test this that would be awesome.

If you have hints how to make this work on AMD Threadripper 7000 Pro series please guide me.

Thanks all!
·
MElHuseyni 
authored a paper 5 days ago
ronantakizawa 
posted an update 6 days ago
view post
Post
1621
Introducing the tiktok-trending-hashtags dataset: a compilation of 1,830 unique trending hashtags on TikTok from 2022 to 2025. This dataset captures viral one-time and seasonal viral moments on TikTok and is perfect for researchers, marketers, and content creators studying viral content patterns on social media.

ronantakizawa/tiktok-trending-hashtags
#tiktok #trends #social-media
ronantakizawa 
posted an update 9 days ago
view post
Post
305
Reached 2500+ total downloads across my models and datasets! 🎉

Follow me for more @ronantakizawa
ronantakizawa 
posted an update 11 days ago
view post
Post
316
Introducing the india-trending-words dataset: a compilation of 900 trending Google searches from 2006-2024 based on https://trends.withgoogle.com. This dataset captures search trends in 80 categories, and is perfect for analyzing cultural shifts and predicting future trends in India.

#india #indiadataset #googlesearches

ronantakizawa/india-trending-words
Nymbo 
posted an update 11 days ago
view post
Post
4643
🚀 I've just shipped a major update to the Nymbo/Tools MCP server: the Agent_Terminal, a single "master tool" that cuts token usage by over 90%!

Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.

# The Problem

Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window — a 10,000-row spreadsheet? That's all going into context just to sum a column.

# The Solution: One Tool to Rule Them All

Agent_Terminal wraps all 12 tools (Web_Search, Web_Fetch, File_System, Generate_Image, Generate_Speech, Generate_Video, Deep_Research, Memory_Manager, Obsidian_Vault, Shell_Command, Code_Interpreter) into a single Python code execution gateway.

Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:

# Search for Bitcoin price
result = Web_Search("current price of bitcoin", max_results=3)
print(result)


Don't know what tools are available? The agent can discover them at runtime:

print(search_tools('image'))  # Find tools by keyword
print(usage('Generate_Image'))  # Get full docs for a specific tool


The individual direct tool calls are all still there, but they can be disabled if using the Agent_Terminal. Try it now - https://www.nymbo.net/nymbot
  • 1 reply
·
ronantakizawa 
posted an update 13 days ago
view post
Post
2456
Introducing the japanese-trending-words dataset: a dataset consisting 593 words from Japan’s annual trending word rankings (流行語大賞) from 2006-2025. This dataset provides the top 30 words from each year and its meaning in Japanese and english. This resource is awesome for NLP tasks understanding recent Japanese culture and history.

ronantakizawa/japanese-trending-words

#japanese #japanesedataset #trending
MElHuseyni 
authored a paper 13 days ago
mitkox 
posted an update 14 days ago
view post
Post
3024
I run 20 AI coding agents locally on my desktop workstation at 400+ tokens/sec with MiniMax-M2. It’s a Sonnet drop-in replacement in my Cursor, Claude Code, Droid, Kilo and Cline peak at 11k tok/sec input and 433 tok/s output, can generate 1B+ tok/m.All with 196k context window. I'm running it for 6 days now with this config.

Today max performance was stable at 490.2 tokens/sec across 48 concurrent clients and MiniMax M2.

Z8 Fury G5, Xeon 3455, 4xA6K. Aibrix 0.5.0, vLLM 0.11.2,
·
MElHuseyni 
authored a paper 16 days ago
ronantakizawa 
posted an update 18 days ago
view post
Post
989
Introducing the google-trending-words dataset: a compilation of 2784 trending Google searches from 2001-2024 based on https://trends.withgoogle.com. This dataset captures search trends in 93 categories, and is perfect for analyzing cultural shifts, predicting future trends, and understanding how global events shape online behavior.

#trends #google #googlesearches

ronantakizawa/trending-words-google
ronantakizawa 
posted an update 20 days ago
view post
Post
1622
Introducing the Japanese Character Difficulty Dataset: a collection of 3,003 Japanese characters (Kanji) labeled with official educational difficulty grades. It includes elementary (grades 1–6), secondary (grade 8), and advanced (grade 9) characters, making it useful for language learning, text difficulty analysis, and educational tool development 🎉

ronantakizawa/japanese-character-difficulty

#japanese #kanji #japanesedataset
ronantakizawa 
posted an update 23 days ago
view post
Post
2285
I built a demo on how to implement Cache-Augmented Generation (CAG) in an LLM and compare its performance gains to RAG (111 stars, 20 forks).

https://github.com/ronantakizawa/cacheaugmentedgeneration

CAG preloads document content into an LLM’s context as a precomputed key-value (KV) cache. This caching eliminates the need for real-time retrieval during inference, reducing token usage by up to 76% while maintaining answer quality.

CAG is particularly effective for constrained knowledge bases like internal documentation, FAQs, and customer support systems, where all relevant information can fit within the model's extended context window.

#rag #retrievalaugmentedgeneration
ronantakizawa 
posted an update 24 days ago
view post
Post
3287
Reached 1000+ total downloads across my models and datasets! 🎉

Follow me for more @ronantakizawa
  • 2 replies
·
ronantakizawa 
posted an update 25 days ago
view post
Post
2971
Introducing the Japanese honorifics dataset: a dataset with 137 sentences covering the three main keigo forms: 尊敬語 (Sonkeigo), 謙譲語 (Kenjōgo), and 丁寧語 (Teineigo). Each entry includes the base form, all three honorific transformations, and English translations for essential phrases in Japanese. This dataset is perfect for training and evaluating the Japanese skill level of LLMs.

#japanese #japanesedataset

ronantakizawa/japanese-honorifics
csabakecskemeti 
posted an update 27 days ago
view post
Post
301
Recently there are so much activity on token efficient formats, I've also build a package (inspired by toon).

Deep-TOON

My goal was to token efficiently handle json structures with complex embeddings.

So this is what I've built on the weekend. Feel free try:

https://pypi.org/project/deep-toon/0.1.0/
mitkox 
posted an update 28 days ago
view post
Post
4122
I just threw Qwen3-0.6B in BF16 into an on device AI drag race on AMD Strix Halo with vLLM:

564 tokens/sec on short 100-token sprints
96 tokens/sec on 8K-token marathons

TL;DR You don't just run AI on AMD. You negotiate with it.

The hardware absolutely delivers. Spoiler alert; there is exactly ONE configuration where vLLM + ROCm + Triton + PyTorch + Drivers + Ubuntu Kernel to work at the same time. Finding it required the patience of a saint

Consumer AMD for AI inference is the ultimate "budget warrior" play, insane performance-per-euro, but you need hardcore technical skills that would make a senior sysadmin nod in quiet respect.
  • 1 reply
·