huggingPartyParis

community

https://partiful.com/e/oWOMGoPxB5D37qw5F8yN

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Nymbo

posted an update 1 day ago

Post

1186

Anthropic gave me six months of Claude Max 20x through the Claude for Open Source program, granted based on my Hugging Face work. Thank you

Anthropic for supporting open source.

So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.

https://github.com/Nymbo/Markdown-Minimap — issues and PRs welcome.

julien-c

posted an update 15 days ago

Post

4148

who's working on an NVFP4 version of Kimi-K3?

4 replies

Nymbo

posted an update 18 days ago

Post

5615

Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.

CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.

See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2

Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)

6 replies

orhir

authored a paper about 1 month ago

SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE

Paper • 2606.32033 • Published Jun 30 • 7

nthngdy

submitted a paper to Daily Papers about 1 month ago

The State-Prediction Separation Hypothesis

Paper • 2607.01218 • Published Jul 1 • 12

orhir

submitted a paper to Daily Papers about 1 month ago

SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE

Paper • 2606.32033 • Published Jun 30 • 7

seppia978

authored a paper about 1 month ago

A Gravitational Interpretation of Fine-Tuning Reversion

Paper • 2606.28525 • Published Jun 26 • 4

seppia978

submitted a paper to Daily Papers about 1 month ago

A Gravitational Interpretation of Fine-Tuning Reversion

Paper • 2606.28525 • Published Jun 26 • 4

seppia978

authored 5 papers about 2 months ago

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks

Paper • 2410.18210 • Published Oct 23, 2024

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

Paper • 2606.10740 • Published Jun 9 • 2

lbourdois

posted an update 2 months ago

Post

1219

New blog post!
An introduction to a little-known but highly effective model reduction method: 𝗧𝗿𝗶𝗺𝗺𝗶𝗻𝗴✂️
We show how to reduce model size (we went up to 87.24% reduction) while preserving its performance.

We applied this technique to 16 different model families across several modalities to illustrate that it works on any architecture (as long as the embedding layer is the last one of the model) and on any modality involving text.
From these 16 families, we generated over 𝟱,𝟱𝟬𝟬 𝗺𝗼𝗻𝗼𝗹𝗶𝗻𝗴𝘂𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀 𝗶𝗻 𝟭𝟮𝟰 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲𝘀 🌍

Key takeaways from our experiments:
1️⃣ Trimming does not require a GPU. Our models were obtained on a CPU.
2️⃣ This method scales up to at least 4B parameters (we did not test beyond that).
3️⃣ Trimmed model is smaller than the original while preserving its performance. If you observe a slight performance drop, just fine-tuned to recover or even surpass the original performance.
4️⃣ For an equivalent compute budget, it is better to trim then fine-tune rather than fine-tuning the original model. Since the model is smaller, you can run more epochs/show more data and get in fine a better model than the original.
5️⃣ Trimming is a competitive alternative to distillation and quantization. E.g. we obtained our alternative to DistilBERT in 9 minutes on CPU vs. 90 hours of GPU for the latter.
6️⃣ Trimming could generate reasoning traces in the language of the trimmed model. This could be an alternative to generating traces in English and then translating them into the desired language.

And many other things (such as how much data are needed, the impact of the database used, the order in which it should be done, etc.) are available in the blogpost!

Blogpost: https://huggingface.co/blog/lbourdois/introduction-to-trimming
Models: alphaedge-ai/Trimming_models_search

4 replies

Eladlev

submitted a paper to Daily Papers 4 months ago

BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate

Paper • 2604.25203 • Published Apr 28 • 8

zbeeb

authored a paper 4 months ago

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published Mar 27 • 148

zbeeb

submitted a paper to Daily Papers 4 months ago

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published Mar 27 • 148

Nymbo

posted an update 5 months ago

Post

7901

We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.

Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.

3 replies

nthngdy

submitted a paper to Daily Papers 5 months ago

Lost in Backpropagation: The LM Head is a Gradient Bottleneck

Paper • 2603.10145 • Published Mar 10 • 13

mariagrandury

authored a paper 6 months ago

BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data

Paper • 2510.10159 • Published Oct 11, 2025 • 3

AI & ML interests

Team members 977

HuggingPartyParis's activity