Hugging Face's logo
PZ's picture
8 35 142

PZ PRO

philipp-zettl
majidml's profile picture 21world's profile picture fatslappa's profile picture
·

AI & ML interests

NLP/CV/Multimodal learning

Recent Activity

reacted to hexgrad's post with 🔥 4 days ago
https://huggingface.co/hexgrad/Kokoro-82M got an upgrade! ⬆️ More voices, more languages, `pip install kokoro`, and still 82M parameters. GitHub: https://github.com/hexgrad/kokoro PyPI: https://pypi.org/project/kokoro/ Space: https://huggingface.co/spaces/hexgrad/Kokoro-TTS
upvoted an article 7 days ago
FineWeb2-C: Help Build Better Language Models in Your Language
reacted to mitkox's post with 🚀 7 days ago
llama.cpp is 26.8% faster than ollama. I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison. Total duration: llama.cpp 6.85 sec <- 26.8% faster ollama 8.69 sec Breakdown by phase: Model loading llama.cpp 241 ms <- 2x faster ollama 553 ms Prompt processing llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster ollama 42.17 tokens/s with an eval time of 498 ms Token generation llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster ollama 122.07 tokens/s with an eval time 7.64 sec llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing. Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
View all activity

Organizations

Blog-explorers's profile picture easybits's profile picture

philipp-zettl's activity

reacted to hexgrad's post with 🔥 4 days ago
upvoted an article 7 days ago
view article
Article

FineWeb2-C: Help Build Better Language Models in Your Language

By davanstrien •
• 18
reacted to mitkox's post with 🚀 7 days ago
view post
Post
2113
llama.cpp is 26.8% faster than ollama.
I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison.

Total duration:
llama.cpp 6.85 sec <- 26.8% faster
ollama 8.69 sec

Breakdown by phase:
Model loading
llama.cpp 241 ms <- 2x faster
ollama 553 ms

Prompt processing
llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster
ollama 42.17 tokens/s with an eval time of 498 ms

Token generation
llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster
ollama 122.07 tokens/s with an eval time 7.64 sec

llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing.

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
·
reacted to fdaudens's post with ❤️ 7 days ago
view post
Post
7878
Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after:

- Original release: 8 models, 540K downloads. Just the beginning...

- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.

The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.

When you empower builders, innovation explodes. For everyone. 🚀

The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.
·
liked 3 models 7 days ago
updated a model 9 days ago
published a model 9 days ago
liked 3 models 10 days ago
liked a dataset 13 days ago
upvoted a paper 21 days ago
liked 2 models about 1 month ago
upvoted a paper about 1 month ago
upvoted a paper about 2 months ago
liked a model about 2 months ago
reacted to lewtun's post with 🚀 about 2 months ago
view post
Post
6821
We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥

How? By combining step-wise reward models with tree search algorithms :)

We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"

We're open sourcing the full recipe and sharing a detailed blog post.

In our blog post we cover:

📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.

🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.

🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM

Here's the links:

- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute

- Code: https://github.com/huggingface/search-and-learn

Enjoy!
  • 2 replies
·