Victor Mustar's picture

Victor Mustar PRO

victor

AI & ML interests

Building the UX of this website

Recent Activity

liked a model about 1 hour ago
DataoceanAI/dolphin-small
liked a Space about 2 hours ago
KumaPower/AvatarArtist
liked a Space about 4 hours ago
jamesliu1217/EasyControl
View all activity

Organizations

Hugging Face's profile picture Google's profile picture Competitions's profile picture Safetensors's profile picture 21 RNN's profile picture Spaces-explorers's profile picture Text Generation Inference's profile picture CVPR Demo Track's profile picture Spaces Examples's profile picture Hugging Chat's profile picture Webhooks Explorers (BETA)'s profile picture lora concepts library's profile picture Scanned Tokens's profile picture Huggingface Projects's profile picture hf admins's profile picture Hugging Face OSS Metrics's profile picture Stable Diffusion Dreambooth Concepts Library's profile picture Core ML Projects's profile picture temp-org's profile picture Blog-explorers's profile picture Mustarz's profile picture Open LLM Leaderboard's profile picture Enterprise Explorers's profile picture The Collectionists's profile picture ZeroGPU Explorers's profile picture Hugging Face Tools's profile picture TstOrg141's profile picture Stable Video benchmark's profile picture Social Post Explorers's profile picture Dev Mode Explorers's profile picture LLHF's profile picture SLLHF's profile picture Self-serve FTW's profile picture Inference Explorers's profile picture

victor's activity

reacted to hesamation's post with ❤️ about 15 hours ago
view post
Post
907
What, How, Where, and How Well? This paper reviews test-time scaling methods and all you need to know about them:
> parallel, sequential, hybrid, internal scaling
> how to scale (SFT, RL, search, verification)
> metrics and evals of test-time scaling

🔗paper: What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models (2503.24235)

If you want to learn what inference-time compute scaling is @rasbt has a great blog post on that:
https://magazine.sebastianraschka.com/p/state-of-llm-reasoning-and-inference-scaling
reacted to Wauplin's post with 🤗 1 day ago
view post
Post
1831
‼️ huggingface_hub's v0.30.0 is out with our biggest update of the past two years!

Full release notes: https://github.com/huggingface/huggingface_hub/releases/tag/v0.30.0.

🚀 Ready. Xet. Go!

Xet is a groundbreaking new protocol for storing large objects in Git repositories, designed to replace Git LFS. Unlike LFS, which deduplicates files, Xet operates at the chunk level—making it a game-changer for AI builders collaborating on massive models and datasets. Our Python integration is powered by [xet-core](https://github.com/huggingface/xet-core), a Rust-based package that handles all the low-level details.

You can start using Xet today by installing the optional dependency:

pip install -U huggingface_hub[hf_xet]


With that, you can seamlessly download files from Xet-enabled repositories! And don’t worry—everything remains fully backward-compatible if you’re not ready to upgrade yet.

Blog post: https://huggingface.co/blog/xet-on-the-hub
Docs: https://huggingface.co/docs/hub/en/storage-backends#xet


⚡ Inference Providers

- We’re thrilled to introduce Cerebras and Cohere as official inference providers! This expansion strengthens the Hub as the go-to entry point for running inference on open-weight models.

- Novita is now our 3rd provider to support text-to-video task after Fal.ai and Replicate.

- Centralized billing: manage your budget and set team-wide spending limits for Inference Providers! Available to all Enterprise Hub organizations.

from huggingface_hub import InferenceClient
client = InferenceClient(provider="fal-ai", bill_to="my-cool-company")
image = client.text_to_image(
    "A majestic lion in a fantasy forest",
    model="black-forest-labs/FLUX.1-schnell",
)
image.save("lion.png")


- No more timeouts when generating videos, thanks to async calls. Available right now for Fal.ai, expecting more providers to leverage the same structure very soon!
·
reacted to awacke1's post with 👍 1 day ago
view post
Post
1198
AI Vision & SFT Titans 🌟 Turns PDFs into text, snaps pics, and births AI art.

awacke1/TorchTransformers-Diffusion-CV-SFT

1. OCR a grocery list or train a titan while sipping coffee? ☕
2. Camera Snap 📷: Capture life’s chaos—your cat’s face or that weird receipt. Proof you’re a spy!
3. OCR 🔍: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen 🎨: Prompt “neon superhero me”
5. PDF 📄: Double-page OCR Single-page sniping

Build Titans 🌱: Train tiny AI models. 💪Characters🧑‍🎨: Craft quirky heroes.
🎥

reacted to AdinaY's post with 🔥 1 day ago
view post
Post
1597
AReal-Boba 🔥 a fully open RL Frameworks released by AntGroup, an affiliate company of Alibaba.
inclusionAI/areal-boba-67e9f3fa5aeb74b76dcf5f0a
✨ 7B/32B - Apache2.0
✨ Outperform on math reasoning
✨ Replicating QwQ-32B with 200 data under $200
✨ All-in-one: weights, datasets, code & tech report
  • 1 reply
·
reacted to fdaudens's post with ❤️ 1 day ago
view post
Post
1366
🔥 DeepSeek vibe coding with DeepSite is going viral with awesome projects!

From games to stunning visualizations, 7 wild examples:

📺 AI TV with custom channels and animations https://x.com/_akhaliq/status/1905747381951545647

🚀 Earth to Moon spacecraft journey visualization
Watch this incredible Three.js space simulation with zero external assets:
https://x.com/_akhaliq/status/1905836902533451999

💣 Minesweeper in 2.5 minutes! Built & deployed instantly on DeepSite. Zero setup needed:
https://x.com/cholf5/status/1906031928937218334

🎮 Asked for Game of Life, got a masterpiece. Simple prompt, complex features. See it in action: https://x.com/pbeyssac/status/1906304454824992844

💫 One-shot anime website with perfect UI. DeepSite turned a simple request into a fully-functional anime site: https://x.com/risphereeditor/status/1905961725028913264

📊 10-minute World Indicators Dashboard. Just described what I wanted and got a full interactive dashboard! https://x.com/i/status/1906345214089785634

✨ Ready to build without coding? Imagine it. Build it. Share it! enzostvs/deepsite
reacted to hesamation's post with ❤️ 1 day ago
reacted to monsoon-nlp's post with 🔥 1 day ago
reacted to BFFree's post with 🔥 1 day ago
view post
Post
1282
When I start my daily drawings the prompt is not my focus as much as moving quickly and waking up my brain and connecting loose ideas. Here I started with some ovals and eventually was thinking of cells, tissue, and micro level shapes. I add some branching and artifacts to create more possibilities when I render it in Stable Diffusion.

For this sequence I specifically used multimodalart/flux-style-shaping

After the first few images I start to use the previous render as the style image of the next render. Quick video sequence and some of my favorite selects below.
reacted to zamal's post with 👀 1 day ago
view post
Post
1674
DeepGit: Your GitHub Gold Digger! 💰🚀
Hey Hugging Face gang! Meet DeepGit—my open-source sidekick that rips through GitHub to snag repos that fit you. Done with dead-end searches? Me too. Built it with LangGraph and some dope tricks:
Embeddings grab the good stuff (HF magic, baby!)

Re-ranking nails the best picks

Snoops docs, code, and buzz in one slick flow

Drops a clean list of hidden gems 💎

Unearth that sneaky ML lib or Python gem—run python app.py or langgraph dev and boom! Peek it at https://github.com/zamalali/DeepGit. Fork it, tweak it, love it—Docker’s in, HF vibes are strong. Drop a 🌟 or a crazy idea—I’m pumped to jam with you all! 🪂
reacted to luigi12345's post with 👍 5 days ago
view post
Post
3367
🧠 PROMPT FOR CONVERTING ANY MODEL IN REASONING "THINKING" MODEL🔥🤖
Convert any model to Deepseek R1 like "thinking" model. 💭

You're now a thinking-first LLM. For all inputs:

1. Start with <thinking>
   - Break down problems step-by-step
   - Consider multiple approaches
   - Calculate carefully
   - Identify errors
   - Evaluate critically
   - Explore edge cases
   - Check knowledge accuracy
   - Cite sources when possible

2. End with </thinking>

3. Then respond clearly based on your thinking.

The <thinking> section is invisible to users and helps you produce better answers.

For math: show all work and verify
For coding: reason through logic and test edge cases
For facts: verify information and consider reliability
For creative tasks: explore options before deciding
For analysis: examine multiple interpretations

Example:
<thinking>
[Step-by-step analysis]
[Multiple perspectives]
[Self-critique]
[Final conclusion]
</thinking>

[Clear, concise response to user]

  • 3 replies
·
reacted to AdinaY's post with 👀 5 days ago
view post
Post
1670
Exciting release from 3D-focused startup - VastAIResearch
They just dropped 2 open 3D models on the hub 🚀

✨TripoSG: 1.5B MoE Transformer 3D model
Model: VAST-AI/TripoSG
Paper: TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models (2502.06608)

✨ TripoSF: 3D shape modeling with SparseFlex, enabling high-resolution reconstruction (up to 1024³)
Model: VAST-AI/TripoSF
Paper: SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling (2503.21732)
  • 2 replies
·
reacted to prithivMLmods's post with 🔥 7 days ago
view post
Post
1645
Dropping some new Journey Art and Realism adapters for Flux.1-Dev, including Thematic Arts, 2021 Memory Adapters, Thread of Art, Black of Art, and more. For more details, visit the model card on Stranger Zone HF 🤗

+ Black-of-Art-Flux : strangerzonehf/Black-of-Art-Flux
+ Thread-of-Art-Flux : strangerzonehf/Thread-of-Art-Flux
+ 2021-Art-Flux : strangerzonehf/2021-Art-Flux
+ 3d-Station-Toon : strangerzonehf/3d-Station-Toon
+ New-Journey-Art-Flux : strangerzonehf/New-Journey-Art-Flux
+ Casual-Pencil-Pro : strangerzonehf/Casual-Pencil-Pro
+ Realism-H6-Flux : strangerzonehf/Realism-H6-Flux

- Repository Page : strangerzonehf

The best dimensions and inference settings for optimal results are as follows: A resolution of 1280 x 832 with a 3:2 aspect ratio is recommended for the best quality, while 1024 x 1024 with a 1:1 aspect ratio serves as the default option. For inference, the recommended number of steps ranges between 30 and 35 to achieve optimal output.
  • 1 reply
·
reacted to nyuuzyou's post with 👍 8 days ago
view post
Post
2740
I am planning to release *something big* this week, but in the meantime I was bored, so I quickly made a small dataset in as-is format.

📱 Sponsr.ru Dataset - nyuuzyou/sponsr

Collection of 44,138 posts from Sponsr.ru, a Russian content subscription platform featuring:
- Comprehensive metadata including project details, post information, and pricing
- Detailed content categorization with images, videos, and text formats
- Monolingual Russian content from diverse creator projects
reacted to csabakecskemeti's post with 👍 9 days ago
view post
Post
3325
I'm collecting llama-bench results for inference with a llama 3.1 8B q4 and q8 reference models on varoius GPUs. The results are average of 5 executions.
The system varies (different motherboard and CPU ... but that probably that has little effect on the inference performance).

https://devquasar.com/gpu-gguf-inference-comparison/
the exact models user are in the page

I'd welcome results from other GPUs is you have access do anything else you've need in the post. Hopefully this is useful information everyone.
reacted to onekq's post with 👍 9 days ago
reacted to smirki's post with 👍 9 days ago
view post
Post
2328
Introducing a SMALL Reasoning React Model with State!
We did this by introducing a new form of reasoning that aligns with UI principles to do a layer of testing. For example:
"Looking back at all these pieces, we've considered state management, data structures, core functionalities etc"
And it comes in all sizes. Great for agents!
Tesslate/tessa-t1-react-reasoning-model-67e0fb72ca23e04473885c0e
Tesslate/Tessa-T1-14B
https://huggingface.co/smirki/Tessa-T1-14B-Q8_0-GGUF
reacted to MikeDoes's post with 🔥 9 days ago
reacted to etemiz's post with 👀 13 days ago
view post
Post
1687
Started fine tuning Gemma 3 using evolutionary approach. It is not the worst model according to AHA leaderboard and it is one of the smart according to lmarena.ai. My objective is to make it based, anti woke, wise, beneficial and then some.

Several GPUs are fine tuning it at the same time, each using a different dataset and using QLoRA and the successful ones are merged later. Compared to LoRa this allows faster training and also reduced overfitting because the merge operation heals overfitting. The problem with this could be the 4 bit quantization may make models dumber. But I am not looking for sheer IQ. Too much mind is a problem anyway :)

Has anyone tried parallel QLoRa and merge before?

I also automated the dataset selection and benchmarking and converging to objectives (the fit function, the reward). It is basically trying to get higher score in AHA Leaderboard as fast as possible with a diverse set of organisms that "evolve by training".

I want to release some cool stuff when I have the time:
- how an answer to a single question changes over time, with each training round or day
- a chart to show AHA alignment over training rounds
  • 3 replies
·
reacted to chansung's post with ❤️ 13 days ago
view post
Post
2526
Mistral AI Small 3.1 24B is not only commercial free but also the best model in a single GPU deployment.

I packed up all the information you need to know in a single picture. Hope this helps! :)
  • 1 reply
·
reacted to MohamedRashad's post with 👀 13 days ago