Post
399
Uncensoring Mistral,
give it a try
s3nh/Ministral-3-14B-Instruct-2512-BF16-abliterated
give it a try
s3nh/Ministral-3-14B-Instruct-2512-BF16-abliterated
AI & ML interests
LowRes animated waifus (✿◡‿◡)
Post
446
Existing methods — GPTQ, AWQ, llama.cpp's k-quants — minimize empirical loss heuristically. None of them prove they are optimal in any information-theoretic sense. ICRB-Q builds a quantization scheme that is provably optimal via the Cramér-Rao lower bound (CRB): no unbiased estimator of a weight can have lower variance than [F(θ)]⁻¹, where F is the Fisher information matrix.
- 1 reply
innovation64
authored a
paper 2 months ago
innovation64
submitted a
paper to Daily Papers 2 months ago
[bot] Conversion to Parquet
#3 opened 6 months ago
by 
parquet-converter
not-lain
updated a
dataset 6 months ago
innovation64
authored a
paper 7 months ago
innovation64
submitted a
paper to Daily Papers 7 months ago
IlyasMoutawwakil
posted an update 7 months ago
Post
3352
Transformers v5 just landed! 🚀
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.
My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇
Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.
In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.
Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.
Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.
Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...
Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.
My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇
Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.
In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.
Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.
Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.
Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...
Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
- 3 replies
IlyasMoutawwakil
posted an update 7 months ago
Post
2491
After 2 months of refinement, I'm happy to announce that a lot of Transformers' modeling code is now significantly more torch-compile & export-friendly 🔥
Why it had to be done 👇
PyTorch's Dynamo compiler is increasingly becoming the default interoperability layer for ML systems. Anything that relies on torch.export or torch.compile, from model optimization to cross-framework integrations, benefits directly when models can be captured as a single dynamo-traced graph !
Transformers models are now easier to:
⚙️ Compile end-to-end with torch.compile backends
📦 Export reliably via torch.export and torch.onnx.export
🚀 Deploy to ONNX / ONNX Runtime, Intel Corporation's OpenVINO, NVIDIA AutoDeploy (TRT-LLM), AMD's Quark, Meta's Executorch and more hardware-specific runtimes.
This work aims at unblocking entire TorchDynamo-based toolchains that rely on exporting Transformers across runtimes and accelerators.
We are doubling down on Transformers commitment to be a first-class citizen of the PyTorch ecosystem, more exportable, more optimizable, and easier to deploy everywhere.
There are definitely some edge-cases that we still haven't addressed so don't hesitate to try compiling / exporting your favorite transformers and to open issues / PRs.
PR in the comments ! More updates coming coming soon !
Why it had to be done 👇
PyTorch's Dynamo compiler is increasingly becoming the default interoperability layer for ML systems. Anything that relies on torch.export or torch.compile, from model optimization to cross-framework integrations, benefits directly when models can be captured as a single dynamo-traced graph !
Transformers models are now easier to:
⚙️ Compile end-to-end with torch.compile backends
📦 Export reliably via torch.export and torch.onnx.export
🚀 Deploy to ONNX / ONNX Runtime, Intel Corporation's OpenVINO, NVIDIA AutoDeploy (TRT-LLM), AMD's Quark, Meta's Executorch and more hardware-specific runtimes.
This work aims at unblocking entire TorchDynamo-based toolchains that rely on exporting Transformers across runtimes and accelerators.
We are doubling down on Transformers commitment to be a first-class citizen of the PyTorch ecosystem, more exportable, more optimizable, and easier to deploy everywhere.
There are definitely some edge-cases that we still haven't addressed so don't hesitate to try compiling / exporting your favorite transformers and to open issues / PRs.
PR in the comments ! More updates coming coming soon !
- 1 reply
potato4code
updated a
collection 9 months ago
Post
1583
The #1 trending AI/ML dataset today 🏆
Massive scale, diversity and end-to-end potential from nvidia !
nvidia/PhysicalAI-Autonomous-Vehicles
Massive scale, diversity and end-to-end potential from nvidia !
nvidia/PhysicalAI-Autonomous-Vehicles
Post
879
The new King 👑has arrived!
Moonshot AI now the top model on Hugging Face 🔥
moonshotai/Kimi-K2-Thinking
Moonshot AI now the top model on Hugging Face 🔥
moonshotai/Kimi-K2-Thinking
Post
2921
💸🤑You don’t need 100 GPUs to train something amazing!
Our Smol Training Playbook teaches you a better path to world-class LLMs, for free!
Check out the #1 trending space on 🤗 :
HuggingFaceTB/smol-training-playbook
Our Smol Training Playbook teaches you a better path to world-class LLMs, for free!
Check out the #1 trending space on 🤗 :
HuggingFaceTB/smol-training-playbook
Post
947
Eduhelp with more empathy, based on model finetuned on
psychotheraputic preferences just landed on
Beck-8B as a base model, 13000 steps on educational dataset.
Time to go further and build more 🥰
s3nh/EduHelp_Beck_8B
Thanks to @basilic_ai for computations <3
psychotheraputic preferences just landed on
Beck-8B as a base model, 13000 steps on educational dataset.
Time to go further and build more 🥰
s3nh/EduHelp_Beck_8B
Thanks to @basilic_ai for computations <3
Post
4428
Just tried to create an educational assistant for younger people who can struggle with visualsation of 'what is this sorcery all about'.
Its first step of my spare time projects, sft on Qwen3-8B,
EduHelper is a child-friendly tutoring assistant fine-tuned from the Qwen3-8B base model using parameter-efficient fine-tuning (PEFT) with LoRA on the ajibawa-2023/Education-Young-Children dataset.
s3nh/EduHelp-8B
Glad to share my work, have a wonderful day!
Its first step of my spare time projects, sft on Qwen3-8B,
EduHelper is a child-friendly tutoring assistant fine-tuned from the Qwen3-8B base model using parameter-efficient fine-tuning (PEFT) with LoRA on the ajibawa-2023/Education-Young-Children dataset.
s3nh/EduHelp-8B
Glad to share my work, have a wonderful day!
- 2 replies
Post
2391
Cool stuff these past weeks on huggingface! 🤗 🚀 !
• 📈Trackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
• 🌍EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
• 💻Open LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
• 🤖Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
• 🖼️Gradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
• 📈Trackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
• 🌍EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
• 💻Open LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
• 🤖Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
• 🖼️Gradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
innovation64
authored a
paper 11 months ago
louisbrulenaudet
posted an update 12 months ago
Post
6579
Supercharge Apple’s Shortcuts using Cloudflare Workers and Gemini within minutes (and for free, up to 1,500 requests per day) ☁️✨
Hello everyone, last week, while experimenting for fun, I created an API that allows you to easily access AI models (in this case, Google's) from the Shortcut app in order to analyze data from my apps and make the most of it thanks to the generative capabilities of advanced models.
It costs me nothing, and I think it might be good to share it so that others can build on it.
In README.md, you will find everything you need to get started and put your own microservice into production, which you can call from the app’s HTTP request features.
You will simply be asked to have a free Cloudflare account and an API key obtained from Google's AI Studio.
Feel free to take a look and get back to me if you encounter any problems during deployment.
Here is the GitHub repo where you can find all the source code and run it on your own: https://github.com/louisbrulenaudet/genai-api
Hello everyone, last week, while experimenting for fun, I created an API that allows you to easily access AI models (in this case, Google's) from the Shortcut app in order to analyze data from my apps and make the most of it thanks to the generative capabilities of advanced models.
It costs me nothing, and I think it might be good to share it so that others can build on it.
In README.md, you will find everything you need to get started and put your own microservice into production, which you can call from the app’s HTTP request features.
You will simply be asked to have a free Cloudflare account and an API key obtained from Google's AI Studio.
Feel free to take a look and get back to me if you encounter any problems during deployment.
Here is the GitHub repo where you can find all the source code and run it on your own: https://github.com/louisbrulenaudet/genai-api
louisbrulenaudet
posted an update 12 months ago
Post
1039
Although more and more code editors are aligning themselves with the AGENTS.md file standard, some still use specific nomenclatures that can make it difficult to maintain different configuration files when several people are working on the same project with different agents.
Bodyboard addresses this by generating canonical instructions for code helpers from a single AGENTS.md file, thereby streamlining the production of adapter outputs for Gemini CLI, Copilot, Cline, Claude, Rules, Windsurf, and OpenAI Codex integrations.
You just have to:
Then run, at the root of your project:
Link to npm: https://www.npmjs.com/package/bodyboard
Link to the GitHub repo: https://github.com/louisbrulenaudet/bodyboard
It's a very simple project, but it addresses certain issues I've encountered, so why not make it available to everyone...
If you have other ideas for adapters to create, feel free to open a PR on the GitHub repo.
Bodyboard addresses this by generating canonical instructions for code helpers from a single AGENTS.md file, thereby streamlining the production of adapter outputs for Gemini CLI, Copilot, Cline, Claude, Rules, Windsurf, and OpenAI Codex integrations.
You just have to:
npm install -g bodyboardThen run, at the root of your project:
bodyboard allLink to npm: https://www.npmjs.com/package/bodyboard
Link to the GitHub repo: https://github.com/louisbrulenaudet/bodyboard
It's a very simple project, but it addresses certain issues I've encountered, so why not make it available to everyone...
If you have other ideas for adapters to create, feel free to open a PR on the GitHub repo.