John6666 (John Smith)

reacted to evalstate's post with 🤗 about 15 hours ago

Post

1314

Hugging Face MCP Server v0.3.2
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

- Replace model_search and dataset_search with combined hub_repo_search tool.
- Less distracting description for hf_doc_search
- model_search and dataset_search tool calls will still function (plan to remove next release).

reacted to soul-muxammad's post with 👍 about 15 hours ago

Post

138

🧠 Introducing TajikGPT — Multilingual AI Platform

We're excited to announce TajikGPT, a multilingual AI platform by SoulLab supporting 50+ languages.

Our model family:
• TJ-1.0 Mini — Fast & lightweight
• TJ-1.0 — Balanced quality & speed
• TJ-1.0 Pro — Advanced reasoning + Vision
• TJ-1.0 Ultra — Maximum performance
• TJ-Coder — Code specialist
• TJ-Image 1.0 — HD image generation
• TJ-Image 0.5 — Fast image generation

🚀 Try the demo: TajikGPT-Team/tajikgpt
🌐 Platform: https://tajikgpt.com
📖 API Docs: https://tajikgpt.com/docs
📦 Python SDK: pip install tajikgpt

All models:

TajikGPT-Team

We'd love your feedback!

1 reply

·

reacted to ajibawa-2023's post with 👍 about 15 hours ago

Post

1374

Java-Code-Large ( ajibawa-2023/Java-Code-Large)

Java-Code-Large is a large-scale corpus of publicly available Java source code comprising more than 15 million java codes. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, software engineering automation, and program analysis.

By providing a high-volume, language-specific corpus, Java-Code-Large enables systematic experimentation in Java-focused model training, domain adaptation, and downstream code understanding tasks.

reacted to DavidAU's post with 🚀 about 15 hours ago

Post

2199

Gemma 3 (1b, 4b, 12b and 27b) - Uncensored full Reasoning/Thinking models fine tuned using top distill datasets.

20 Gemma 3 models 1B, 4B, 12B and 27B with full reasoning using GLM 4.7 Flash, GPT, Claude and Gemini datasets and more fully fine tuned using Unsloth.

Most models are Heretic'ed (uncensored) first, and tuned second.
This vastly improves the model.

Models are also bench marked and in almost all cases exceed org model metrics - and in some cases by a lot.

Enjoy the freedom and more powerful THINKING/REASONING and UNCENSORED Gemma 3s !

https://huggingface.co/collections/DavidAU/gemma-3-reasoning-thinking-models-incl-uncensored

reacted to illinicraig's post with 👀 about 15 hours ago

Post

152

I’m getting a 402 on any huggingchat query. The 402 is returned from the web-search-exa query. Looks like others are experiencing the same.

2 replies

·

replied to illinicraig's post about 15 hours ago

I couldn't reproduce it just now, but it seems others are experiencing the same error. Maybe it's best to report it in this thread.
https://huggingface.co/spaces/huggingchat/chat-ui/discussions/764

reacted to danielhanchen's post with 🔥 about 15 hours ago

Post

4252

You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.

GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.

Guide: https://unsloth.ai/docs/models/qwen3.5

7 replies

·

reacted to prithivMLmods's post with 🔥🤗 about 15 hours ago

Post

1663

Dropping the Qwen3 VL Series of Unredacted MAX-VL models. These models have undergone multi-stage training to minimize refusal rates through continuous abliterated optimization. You can find the models in BF16, FP8-Dynamic, and GGUF formats at the links below.🔥🚀

Unredacted MAX - VL:
➜ prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX
➜ prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX
➜ prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX
➜ prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX

Unredacted MAX - VL [FP8]
➜ prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX-FP8
➜ prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX-FP8
➜ prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-FP8
➜ prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-FP8

Unredacted MAX - VL [GGUF]
➜ prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX-GGUF
➜ prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX-GGUF
➜ prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-GGUF
➜ prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF

Unredacted MAX - VL [Collection]
➜ https://huggingface.co/collections/prithivMLmods/unredacted-max-vl-fp8
➜ https://huggingface.co/collections/prithivMLmods/unredacted-max-vl
➜ https://huggingface.co/collections/prithivMLmods/unredacted-max-vl-gguf

To learn more, visit the app page or the respective model pages.

reacted to demirytu's post with 👀 about 15 hours ago

Post

1431

is the chat feature down? recently I can not have success to get responses for my prompts.

1 reply

·

replied to demirytu's post about 15 hours ago

Hmm... You can contact maintainers via https://huggingface.co/spaces/huggingchat/chat-ui/discussions

reacted to Ujjwal-Tyagi's post with 🔥 about 15 hours ago

Post

140

Qwen 3.5 Model is here! Supporting 1m context length by default, It is giving much good performance and competitive to Claude Opus 4.6, Qwen/Qwen3.5-397B-A17B, here it's GGUF: unsloth/Qwen3.5-397B-A17B-GGUF, Follow me and turn on the notification for the latest news!

reacted to ronantakizawa's post with 👍 about 15 hours ago

Post

133

Introducing the LeetCode Assembly Dataset: a dataset of 400+ LeetCode problem solutions in assembly across x86-64, ARM64, MIPS64, and RISC-V using GCC & Clang at -O0/-O1/-O2/-O3 optimizations.

This dataset is perfect for teaching LLMs complex compiler behavior!

#dataset #leetcode #assembly

ronantakizawa/leetcode-assembly

reacted to MikeDoes's post with 👀 about 15 hours ago

Post

142

State-of-the-art AI doesn't start with a model. It starts with the data.

Achieving near-perfect accuracy for PII & PHI

anonymization is one of the toughest challenges in NLP. A model is only as good as the data it learns from, providing this foundational layer is central to our mission. The

ai4privacy/pii-masking-400k dataset was built for this exact purpose: to serve as a robust, large-scale, open-source training ground for building high-precision privacy tools.

To see the direct impact of this data-first approach, look at the ner_deid_aipii model for Healthcare NLP by johnsnow lab. By training on our 400,000 labeled examples, the model achieved incredible performance:

100% F1-score on EMAIL detection.

99% F1-score on PHONE detection.

97% F1-score on NAME detection.

This is the result of combining a cutting-edge architecture with a comprehensive, high-quality dataset. We provide the open-source foundation so developers can build better, safer solutions.

Explore the dataset that helps power these next-generation privacy tools: ai4privacy/pii-masking-400k

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

#DataPrivacy #AI #OpenSource #Anonymization #MachineLearning #HealthcareAI #Ai4Privacy

reacted to danielhanchen's post with 🔥 2 days ago

Post

7997

You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.

Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF

1 reply

·

reacted to krisbailey's post with 👀 3 days ago

Post

420

While doing various projects I kept running into situations where I wanted to be able to have representative samples of some of the current large SOTA datasets that were smaller so I didn't need to worry about slicing or anything else at runtime. So, I created sub datasets making sure to keep the same ratios of data sources. Each dataset card provides info for what's in it.
100M token datasets:
RedPajama v2 100M
Falcon RefinedWeb 100M
Cosmopedia 100M

1B token datasets:
Fineweb-edu 1B
RedPajama v1 1B
RedPajama v2 1B (use this one)
Cosmopedia 1B

10B token datasets:
RedPajama v1 10B
Cosmopedia 10B

Collection here:
https://huggingface.co/collections/krisbailey/bite-size-data

replied to NeoCodes-dev's post 3 days ago

Oh, i see...

Why this happens

Personal “Articles / Community Blog” is a HF PRO feature, but access is also commonly gated via the blog-explorers org, so the UI may still say “need PRO” even when you’re subscribed. (Hugging Face)
Organization-published Articles are not covered by personal PRO; they require an org on Team/Enterprise and the right org permissions. (Hugging Face)

What to do (short, step-by-step)

Confirm you’re logged into the correct HF account and that PRO is active
- PRO includes “Articles: write and publish blog articles on your HF profile.” (Hugging Face)
Request access to the Community Blog editor gate
- Go to blog-explorers and click “Request to join this org”. This is the documented unlock path. (Hugging Face)
Create the article from the official editor URL
- Use https://huggingface.co/new-blog to start writing once your access is enabled. (Hugging Face)
If you’re trying to publish under a team/org name (not your personal profile)
- Make sure the organization is on Team/Enterprise, and your org role is write or admin. (Hugging Face)
If it still says “need PRO” after #2–#3 (likely an entitlement/account sync issue)
- Email billing@huggingface.co with your username + screenshot of the error + proof your PRO is active. (Hugging Face)

That’s the shortest reliable path: (1) correct account + active PRO → (2) join blog-explorers → (3) use /new-blog → (4) handle org vs personal publishing → (5) billing support if still blocked.

reacted to NeoCodes-dev's post with 👀 3 days ago

Post

266

Hi all,

I am working on a project for the Pytorch/HF OpenEnv challenge, and part of the challenge is that a participant/team needs to write a blog post (an Article) on HuggingFace about their submission. However, when I try to create an Article, it says I need a "pro" account.. but I already am a HF Pro member and have been for almost a year!

Is anyone else having this issue? I have a bunch of ideas for blog posts/articles so I'd really like to be able to access this feature, even outside of the OpenEnv Challenge. Can someone let me know if there's a way to fix this or something I'm missing?

Thanks,
Neo

1 reply

·

reacted to Janady07's post with 🧠 3 days ago

Post

4637

Here is one of the equations that make up the worlds first Artificial General Intelligence. Remember when building Artificial Intelligence or anything on a device it all starts out binary. Everything starts out with data flow physics and mathmatics

6 replies

·

reacted to yuriyvnv's post with 🚀 3 days ago

Post

287

🎯 WAVe-1B-Multimodal-NL: Word-Level Speech Quality Assessment for Dutch

Following the release of the Portuguese model, we're releasing the Dutch variant of WAVe — a 1B multimodal embedding model that assesses synthetic speech quality at the word level, thereby improving the quality of synthetically augmented datasets for training ASR models.

Trained on CommonVoice 16.1 Dutch with 5 corruption strategies, this model catches mispronunciations, timing errors, and prosody issues in synthetic data that sentence-level embeddings miss entirely.
Resources

- Dutch model: yuriyvnv/WAVe-1B-Multimodal-NL
- Portuguese model: yuriyvnv/WAVe-1B-Multimodal-PT
- Code: https://github.com/yuriyvnv/WAVe

This model builds on CommonVoice Dutch data — thanks to @mozilla and the CommonVoice community for making multilingual speech data accessible.

Would be great to hear from the Dutch NLP community — @BramVanroy @GroNLP — especially if you're working on Dutch ASR or TTS pipelines where quality filtering could help. Also tagging @hf-audio as this sits at the intersection of speech processing and data curation.

John Smith PRO

AI & ML interests

Recent Activity

Organizations

Why this happens

What to do (short, step-by-step)

John Smith PRO

AI & ML interests

Recent Activity

Organizations

John6666's activity

Why this happens

What to do (short, step-by-step)