Victor Mustar's picture

Victor Mustar PRO

victor

AI & ML interests

Building the UX of this website

Recent Activity

Organizations

Hugging Face's profile picture Google's profile picture Safetensors's profile picture Competitions's profile picture 21 RNN's profile picture Spaces-explorers's profile picture Text Generation Inference's profile picture Spaces Examples's profile picture CVPR Demo Track's profile picture Hugging Chat's profile picture Webhooks Explorers (BETA)'s profile picture lora concepts library's profile picture Huggingface Projects's profile picture Scanned Tokens'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 csabakecskemeti's post with πŸ‘ about 1 hour ago
view post
Post
1569
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 πŸ‘ about 1 hour ago
reacted to smirki's post with πŸ‘ about 1 hour ago
view post
Post
434
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 πŸ”₯ about 1 hour ago
reacted to etemiz's post with πŸ‘€ 4 days ago
view post
Post
1649
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
Β·
reacted to chansung's post with ❀️ 4 days ago
view post
Post
2403
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
Β·
reacted to MohamedRashad's post with πŸ‘€ 4 days ago
reacted to sharpenb's post with πŸ”₯ 4 days ago
view post
Post
2997
We open-sourced the pruna package that can be easily installed with pip install pruna :) It allows to easily ccompress and evaluate AI models including transformers and diffusers.

- Github repo: https://github.com/PrunaAI/pruna
- Documentation: https://docs.pruna.ai/en/stable/index.html

With open-sourcing, people can now inspect and contribute to the open code. Beyond the code, we provide detailed readme, tutorials, benchmarks, and documentation to make transparent compression, evaluation, and saving/loading/serving of AI models.

Happy to share it with you and always interested in collecting your feedback :)
  • 1 reply
Β·
reacted to daavoo's post with πŸ”₯ 4 days ago
view post
Post
1956
πŸ€– πŸ—ΊMapped all(?) the swimming pools ️🏊 around another town with https://github.com/mozilla-ai/osm-ai-helper.

This time, I have mapped and contributed to https://www.openstreetmap.org more than 100 swimming pools around my wife's hometown. Only took about 20min to find them all (+~3 min verification) in a free Colab GPUπŸš€

Try it yourself around a single point: mozilla-ai/osm-ai-helper
reacted to clem's post with πŸ”₯ 4 days ago
view post
Post
2354
Nice new space to see how fast your personal or organization followers are growing on HF:
julien-c/follow-history

As you can see, I still have more followers than @julien-c even if he's trying to change this by building such cool spaces 😝😝😝
reacted to csabakecskemeti's post with 😎 5 days ago
reacted to MikeDoes's post with πŸ‘€ 5 days ago
view post
Post
2052
#PII Masking Tech that does not **** around!

We are happy to release the OpenPII English Anonymiser β€”the most powerful open-source tool for redacting sensitive info from English text.

Fine-tuned Modernbert on 5.7 million+ PII examples, it’s clocking 99%+ accuracy across emails, dates, social numbers, and more!

Why it’s a big deal:
βœ… Top-tier precision: 100% for passport numbers, 99.96% for emails*.
βœ… Totally free: MIT license for personal or commercial use.
βœ… No secrets: Full metrics shared on Hugging Face.

#AI #OpenSource #DataSecurity @huggingface

Day 2 out 7 of PII-Masking-1M Announcements Complete!

*Accuracies reported from the new OpenPII-500k dataset

ai4privacy/llama-ai4privacy-english-anonymiser-openpii
reacted to AdinaY's post with πŸ”₯ 5 days ago
reacted to Jaward's post with πŸš€ 5 days ago
view post
Post
2053
Nvidia brings blue (from starwars droids) to life 🀯, supercute with flawless dexterity and droid voice. It's the result of their colab research with Google DeepMind and Disney, revealed as part of their new opensource physics engine for robotics simulation: NEWTON - which enables robots to learn how to complete complex tasks with greater precision.

ReadMore: https://developer.nvidia.com/blog/announcing-newton-an-open-source-physics-engine-for-robotics-simulation?ncid=so-twit-820797-vt48
reacted to mrfakename's post with πŸ‘ 5 days ago
reacted to etemiz's post with πŸ‘ 6 days ago
replied to onekq's post 6 days ago
reacted to onekq's post with πŸš€ 6 days ago
view post
Post
2240
Introducing πŸŽ‰ OneSQL-v0.1πŸ₯³, our first text-to-SQL model based on Qwen2.5-Coder. This model has achieved an EX score of 63.33 on the BIRD leaderboard (https://bird-bench.github.io/).

The model family includes 7B and 32B,
onekq-ai/onesql-v01-qwen-67d8e3eb1611c5532bb90c5f
and can be also found on Ollama (https://ollama.com/onekq/OneSQL-v0.1-Qwen)

My goal is to make OneSQL the most usable open-weights model for text-to-SQL. I'm currently working on best practices to help users use this model the right away and avoid pitfalls. After that, I plan to train the next version to push for a higher EX score.

Enjoy this model and feel free to share comments/questions πŸ€—
  • 1 reply
Β·
reacted to AdinaY's post with πŸš€ 6 days ago
reacted to jasoncorkill's post with 🧠 6 days ago
view post
Post
3754
At Rapidata, we compared DeepL with LLMs like DeepSeek-R1, Llama, and Mixtral for translation quality using feedback from over 51,000 native speakers. Despite the costs, the performance makes it a valuable investment, especially in critical applications where translation quality is paramount. Now we can say that Europe is more than imposing regulations.

Our dataset, based on these comparisons, is now available on Hugging Face. This might be useful for anyone working on AI translation or language model evaluation.

Rapidata/Translation-deepseek-llama-mixtral-v-deepl
  • 1 reply
Β·