victor (Victor Mustar)

reacted to nyuuzyou's post with 👍 1 day ago

Post

5407

🇷🇺 Russian Forum Messages Dataset - nyuuzyou/ruforum

Collection of approximately 58 million Russian forum messages featuring:

- Complete message content from Russian online forums spanning 2010-2025
- Comprehensive metadata including unique message IDs and timestamps
- Full text content preserving original user discussions and interactions
- Monolingual dataset focused exclusively on Russian language content

This dataset offers a unique textual archive of Russian online conversations suitable for text generation, sentiment analysis, and language modeling research. Released to the public domain under CC0 1.0 license.

reacted to AdinaY's post with ❤️ 1 day ago

Post

3098

🔥 New reasoning models from the Chinese community, by Skywork 天工-昆仑万维

Skywork/skywork-or1-67fa1bcb41b436ef2def76b9

✨Skywork OR1-Math-7B > Optimized for math reasoning
✨Skywork-OR1-7B-preview > Excels in math & coding
✨Skywork-OR1-32B-preview > Matches Deepseek-R1 on math (AIME24/25) and coding (LiveCodeBench)

Released under the Apache 2.0 license 🥳
Final version coming in 2 weeks!

reacted to thomwolf's post with 🚀 1 day ago

Post

4130

If you've followed the progress of robotics in the past 18 months, you've likely noticed how robotics is increasingly becoming the next frontier that AI will unlock.

At Hugging Face—in robotics and across all AI fields—we believe in a future where AI and robots are open-source, transparent, and affordable; community-built and safe; hackable and fun. We've had so much mutual understanding and passion working with the Pollen Robotics team over the past year that we decided to join forces!

You can already find our open-source humanoid robot platform Reachy 2 on the Pollen website and the Pollen community and people here on the hub at

pollen-robotics

We're so excited to build and share more open-source robots with the world in the coming months!

1 reply

·

reacted to bartowski's post with 👍 1 day ago

Post

6272

Access requests enabled for latest GLM models

While a fix is being implemented (https://github.com/ggml-org/llama.cpp/pull/12957) I want to leave the models up for visibility and continued discussion, but want to prevent accidental downloads of known broken models (even though there are settings that could fix it at runtime for now)

With this goal, I've enabled access requests. I don't really want your data, so I'm sorry that I don't think there's a way around that? But that's what I'm gonna do for now, and I'll remove the gate when a fix is up and verified and I have a chance to re-convert and quantize!

Hope you don't mind in the mean time :D

reacted to prithivMLmods's post with 👍 1 day ago

Post

2153

Try out the demo for Multimodal OCR featuring the implementation of models including RolmOCR and Qwen2VL OCR. The use case showcases image-text-to-text conversion and video understanding support for the RolmOCR model ! 🚀

🤗Multimodal OCR Space : prithivMLmods/Multimodal-OCR

📦The models implemented in this Space are:
+ Qwen2VL OCR : prithivMLmods/Qwen2-VL-OCR-2B-Instruct [ or ]
+ Qwen2VL OCR2 : prithivMLmods/Qwen2-VL-OCR2-2B-Instruct
+ RolmOCR : reducto/RolmOCR

Qwen2VL OCR supports only image-text-to-text in the space.

reacted to luigi12345's post with 🚀 1 day ago

Post

1805

BREAKING NEWS! 🚀 OpenAI’s GPT-4.1 API Models Are Here – Built for Developers

OpenAI has launched GPT-4.1, GPT-4.1 Mini, and GPT-4.1 Nano—models engineered for real-world coding, instruction following, and long-context tasks.

🔧 Key Dev Features
• Coding Performance: GPT-4.1 scores 54.6% on SWE-bench Verified, outperforming GPT-4o by 21.4% and GPT-4.5 by 26.6%. It handles diffs more precisely, reduces unnecessary edits, and adheres to formatting constraints.
• Long Context: All models support up to 1 million tokens—8x more than GPT-4o—enabling full repo analysis and deep document comprehension.
• Instruction Following: Improved multi-step reasoning and formatting accuracy, with a 10.5% gain over GPT-4o on MultiChallenge.
• Latency & Cost: GPT-4.1 is 40% faster and 80% cheaper per query than GPT-4o. Mini and Nano versions offer even greater speed and affordability.

🧠 Model Lineup

Model Context Window Use Case Cost per 1M Tokens
GPT-4.1 1M tokens Production-grade coding & agents $2.00 input / $8.00 output
GPT-4.1 Mini 1M tokens Balanced performance, cost-sensitive apps $0.40 / $1.60
GPT-4.1 Nano 1M tokens Ultra-fast, lightweight tasks $0.10 / $0.40

🛠️ Access & Tools
• API Only: Available via OpenAI API and Playground—ChatGPT remains on GPT-4o.
• Prompting Guide: Optimized prompts for agentic coding workflows.
• Benchmarks & Pricing: Detailed comparisons and cost breakdowns.

For more information, [visit the official announcement](https://openai.com/index/gpt-4-1)

reacted to neph1's post with 🚀 1 day ago

Post

2113

I know Hunyuan Video is yesterday's jam, but in case you're looking for some cinematic LoRA's (and don't like civitai for some reason), I've uploaded my most popular ones to hf. They are:
1980s fantasy: neph1/1980s_Fantasy_Movies_Hunyuan_Video_Lora
1950s scifi: neph1/50s_scifi_hunyuan_video_lora
1920s horror: neph1/1920s_horror_hunyuan_video_lora

reacted to davidberenstein1957's post with 👀 1 day ago

Post

1141

RealHarm: A Collection of Real-World Language Model Application Failure

I'm David from Giskard, and we work on securing your Agents.
Today, we are launching RealHarm: a dataset of real-world problematic interactions with AI agents, drawn from publicly reported incidents.

Check out the dataset and paper: https://realharm.giskard.ai/

reacted to Yehor's post with 🚀 1 day ago

Post

2032

Made a workable program that uses IREE runtime using Rust to inference wav2vec2-bert model for Automatic Speech Recognition.

reacted to ZennyKenny's post with 👀 8 days ago

Post

2755

Just signed up for the Reasoning Datasets Competition from Hugging Face, Together AI, and Bespoke Labs!

Looking forward to seeing what the community comes up with to help train better reasoning models.

Join the fray: https://www.bespokelabs.ai/blog/reasoning-datasets-competition

4 replies

·

reacted to ajibawa-2023's post with 👍 8 days ago

Post

3852

Hi All, I recently released two Audio datasets which are generated using my earlier released dataset: ajibawa-2023/Children-Stories-Collection

First Audio Dataset:https://huggingface.co/datasets/ajibawa-2023/Audio-Children-Stories-Collection-Large has 5600++ stories in .mp3 format.

Second Audio Dataset:https://huggingface.co/datasets/ajibawa-2023/Audio-Children-Stories-Collection has 600 stories in .mp3 format.

3 replies

·

reacted to daavoo's post with 👀 8 days ago

Post

2786

Wondering how the new Google Agent Development Toolkit (ADK) compares against other frameworks? 🤔You can try it in any-agent 🚀

https://github.com/mozilla-ai/any-agent

agent = AnyAgent.create(
    AgentFramework("google"),
    AgentConfig(
        model_id="gpt-4o-mini"
    )
)
agent.run("Which Agent Framework is the best??")

1 reply

·

reacted to fdaudens's post with ➕ 8 days ago

Post

4041

🎨 Designers, meet OmniSVG! This new model helps you create professional vector graphics from text/images, generate editable SVGs from icons to detailed characters, convert rasters to vectors, maintain style consistency with references, and integrate into your workflow.

@OmniSVG

2 replies

·

reacted to danielhanchen's post with 🔥🤗 9 days ago

Post

4583

You can now run Llama 4 on your own local device! 🦙
Run our Dynamic 1.78-bit and 2.71-bit Llama 4 GGUFs:
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF

You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4

1 reply

·

reacted to jsulz's post with 🔥 9 days ago

Post

2899

What does it mean when models share the same bytes?

We've investigated some quants and have seen that a considerable portion of quantizations of the same model share the same bytes and can be deduplicated to save considerable upload time for quantizers on the Hub.

This space where we crack open a repo from @bartowski shows we can get significant dedupe xet-team/quantization-dedup

You can get a sense of why by reading this write-up: https://github.com/bartowski1182/llm-knowledge/blob/main/quantization/quantization.md

But what about finetuned models?

Since going into production the

xet-team has migrated hundreds of repositories on the Hub to our storage layer, including classic "pre-Hub" open-source models like FacebookAI/xlm-roberta-large (XLM-R) from

FacebookAI

XLM-R, introduced in 2019, set new benchmarks for multilingual NLP by learning shared representations across 100 languages. It was then fine-tuned on English, Spanish, Dutch, and German, generating language-specific derivations for each - check out the paper here Unsupervised Cross-lingual Representation Learning at Scale (1911.02116)

These finetunes share much of the same architecture and layout as XLM-R with similar training methods and goals. It makes sense that they would share bytes, but it's still fascinating to see.

We put together a similar space to explore these models to see where they overlap - check it out for yourself xet-team/finetune-dedupe

The darker each block in the heatmap, the more the bytes are shared. Clicking on a repos blocks shows all other repos that share blocks.

1 reply

·

reacted to Steven10429's post with 👀 9 days ago

Post

2781

I got rejected from llama4.
So that means I can use quantinized model without following their TOS.
Interesting.

3 replies

·

reacted to merterbak's post with 🔥👀 9 days ago

Post

4647

Qwen 3 can launch very soon. 👀

https://github.com/ggml-org/llama.cpp/pull/12828

3 replies

·

reacted to as-cle-bert's post with 🔥 11 days ago

Post

2883

Llama-4 is out and I couldn't resist but to cook something with it... So I came up with 𝐋𝐥𝐚𝐦𝐚𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐞𝐫 (https://llamaresearcher.com), your deep-research AI companion!🔎

The workflow behind 𝗟𝗹𝗮𝗺𝗮𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵𝗲𝗿 is simple:
💬 You submit a query
🛡️ Your query is evaluated by Llama 3 guard model, which deems it safe or unsafe
🧠 If your query is safe, it is routed to the Researcher Agent
⚙️ The Researcher Agent expands the query into three sub-queries, with which to search the web
🌐 The web is searched for each of the sub-queries
📊 The retrieved information is evaluated for relevancy against your original query
✍️ The Researcher Agent produces an essay based on the information it gathered, paying attention to referencing its sources

The agent itself is also built with easy-to-use and intuitive blocks:
🦙 LlamaIndex provides the agentic architecture and the integrations with the language models
⚡Groq makes Llama-4 available with its lightning-fast inference
🔎 Linkup allows the agent to deep-search the web and provides sourced answers
💪 FastAPI does the heavy loading with wrapping everything within an elegant API interface
⏱️ Redis is used for API rate limiting
🎨 Gradio creates a simple but powerful user interface

Special mention also to Lovable, which helped me build the first draft of the landing page for LlamaResearcher!💖

If you're curious and you want to try LlamaResearcher, you can - completely for free and without subscription - for 30 days from now ➡️ https://llamaresearcher.com
And if you're like me, and you like getting your hands in code and build stuff on your own machine, I have good news: this is all open-source, fully reproducible locally and Docker-ready🐋
Just go to the GitHub repo: https://github.com/AstraBert/llama-4-researcher and don't forget to star it, if you find it useful!⭐

As always, have fun and feel free to leave your feedback✨

2 replies

·

Victor Mustar PRO

AI & ML interests

Recent Activity

Organizations

victor's activity