Vibe Check Translations
📈
A/B test translations
AI & ML interests
None defined yet.
Recent Activity
View all activity
guipenedo
updated
a
Space
10 days ago
guipenedo
published
a
Space
15 days ago
Post
4589
Kimi K2 tech report is full of gems as always. Here are my notes on it:
> MuonClip: Pretty crazy how after 70k the training stabilizes and the QK-clip is basically inactive. There is also no loss in perf with QK-clip which is not trivial at all (at small scale but with aggressive threshold). Also a cool explanation of why muon makes the logit explode in appendix E (tl;dr is that muon makes the singular value of the update matrix higher)
> Sparsity scaling laws to justify their ratio, they have a very solid training infra that allows the model to be trained at this sparsity level, they could have increased even more but as sparsity increases the training becomes less efficient.
> They diminish the number of attention heads to make it more efficient for long context since attention heads are a big bottleneck for long context. They also remove 2 of the 3 "first dense" layers in the dsv3 arch.
With the sparsity and attention heads (divided by 2) they achieve 83% increased flops compared to deepseek v3 arch at 128k.
> Data: Rephrasing is KEY. They do a lot more synthetic data generation and rephrase their corpus to have different styles, for longer documents they do it by chunk. I'm (half) surprised by the fact that ONLY 1 epoch (assuming same number of training tokens I think?) of data rephrased 10 times has better accuracy than 10 epochs of the same data rephrased once.
> They do rewriting for Math and Knowledge, for Math they apply the ShallowMath recipe and instruct the model to rephrase in a "learning note" style
> They talk about diversity and probably have some internal stuff/eval to test that, as always still a bit unclear for me how to properly measure that.
The infra is also very nice, quick summary:
> PP=16 (1F1B schedule, a bit custom), EP=16, zero1
> No FP8 computation but for storage of specific layers, selective recomputation for inexpensive block, activation offloading to CPU
> MuonClip: Pretty crazy how after 70k the training stabilizes and the QK-clip is basically inactive. There is also no loss in perf with QK-clip which is not trivial at all (at small scale but with aggressive threshold). Also a cool explanation of why muon makes the logit explode in appendix E (tl;dr is that muon makes the singular value of the update matrix higher)
> Sparsity scaling laws to justify their ratio, they have a very solid training infra that allows the model to be trained at this sparsity level, they could have increased even more but as sparsity increases the training becomes less efficient.
> They diminish the number of attention heads to make it more efficient for long context since attention heads are a big bottleneck for long context. They also remove 2 of the 3 "first dense" layers in the dsv3 arch.
With the sparsity and attention heads (divided by 2) they achieve 83% increased flops compared to deepseek v3 arch at 128k.
> Data: Rephrasing is KEY. They do a lot more synthetic data generation and rephrase their corpus to have different styles, for longer documents they do it by chunk. I'm (half) surprised by the fact that ONLY 1 epoch (assuming same number of training tokens I think?) of data rephrased 10 times has better accuracy than 10 epochs of the same data rephrased once.
> They do rewriting for Math and Knowledge, for Math they apply the ShallowMath recipe and instruct the model to rephrase in a "learning note" style
> They talk about diversity and probably have some internal stuff/eval to test that, as always still a bit unclear for me how to properly measure that.
The infra is also very nice, quick summary:
> PP=16 (1F1B schedule, a bit custom), EP=16, zero1
> No FP8 computation but for storage of specific layers, selective recomputation for inexpensive block, activation offloading to CPU
NXz64Fdf8Y
authored
a
paper
about 1 month ago
thomwolf
authored
a
paper
about 2 months ago
lvwerra
authored
a
paper
about 2 months ago
mjaggi
authored
a
paper
about 2 months ago
negar-foroutan
authored
a
paper
about 2 months ago
vsabolcec
authored
a
paper
about 2 months ago
hynky
authored
a
paper
about 2 months ago
guipenedo
authored
a
paper
about 2 months ago
Post
1638
🤗 Here’s a fun educational video I made to show how Sheets and AI can upgrade your structured content.
Better tables and clearer messages with just a little help from open-source AI!
aisheets/sheets
Better tables and clearer messages with just a little help from open-source AI!
aisheets/sheets
Post
1765
With Sheets, try a new way to create structured content with the help of AI!
No installs. No login. Just open a link and 🤩
This app lets you create a dataset by importing a file or starting from a prompt.
What’s different about SHEETS?
🔎 Web search integration to ground answers in real-world data
📚 In-context learning from validated sources
🔗 Transparent sourcing — every result is linked
🧩 Runs on multiple open-source models
Fight hallucinations and start creating content you can rely on.
No installs. No login. Just open a link and 🤩
This app lets you create a dataset by importing a file or starting from a prompt.
What’s different about SHEETS?
🔎 Web search integration to ground answers in real-world data
📚 In-context learning from validated sources
🔗 Transparent sourcing — every result is linked
🧩 Runs on multiple open-source models
Fight hallucinations and start creating content you can rely on.
dvilasuero
posted
an
update
2 months ago
Post
2789
Super excited to launch Hugging Face Sheets: Spreadsheets meet AI and unstructured data.
A few months ago, we started imagining new ways to build and transform datasets with the latest open-source models.
Today, I'm thrilled to introduce our first step in this direction.
In a nutshell:
📁 Effortlessly run prompts and models over your data.
🌐 Agentic search for accuracy and real-time information.
🖼️ Familiar, minimalistic interface for interacting with data.
🎯 Human feedback 2.0: Your input directly improves generated data.
💯 Access hundreds of open models and leading inference providers.
Go to this space to try it out!
aisheets/sheets
Leave your questions below, we're just getting started!
A few months ago, we started imagining new ways to build and transform datasets with the latest open-source models.
Today, I'm thrilled to introduce our first step in this direction.
In a nutshell:
📁 Effortlessly run prompts and models over your data.
🌐 Agentic search for accuracy and real-time information.
🖼️ Familiar, minimalistic interface for interacting with data.
🎯 Human feedback 2.0: Your input directly improves generated data.
💯 Access hundreds of open models and leading inference providers.
Go to this space to try it out!
aisheets/sheets
Leave your questions below, we're just getting started!
-
- 3 replies
davanstrien
posted
an
update
2 months ago
Post
3359
Inspired by Hugging Face's official MCP server, I've developed a complementary tool that exposes my semantic search API to enhance discovery across the HF platform.
Key capabilities:
- AI-powered semantic search for models and datasets
- Parameter count analysis via safetensors metadata
- Trending content discovery
- Find similar models/datasets functionality
- 11 tools total for enhanced ecosystem navigation
The semantic search goes beyond simple keyword matching, understanding context and relationships between different models and datasets.
Example query: "Find around 10 reasoning Hugging Face datasets published in 2025 focusing on topics other than maths and science. Show a link and a short summary for each dataset." (results in video!)
https://github.com/davanstrien/hub-semantic-search-mcp
Key capabilities:
- AI-powered semantic search for models and datasets
- Parameter count analysis via safetensors metadata
- Trending content discovery
- Find similar models/datasets functionality
- 11 tools total for enhanced ecosystem navigation
The semantic search goes beyond simple keyword matching, understanding context and relationships between different models and datasets.
Example query: "Find around 10 reasoning Hugging Face datasets published in 2025 focusing on topics other than maths and science. Show a link and a short summary for each dataset." (results in video!)
https://github.com/davanstrien/hub-semantic-search-mcp
- 1 reply
loubnabnl
authored
a
paper
2 months ago
guipenedo
authored
a
paper
2 months ago
eliebak
authored
a
paper
2 months ago
thomwolf
authored
a
paper
2 months ago
Post
3723
SmolVLM is now available on PocketPal — you can run it offline on your smartphone to interpret the world around you. 🌍📱
And check out this real-time camera demo by @ngxson , powered by llama.cpp:
https://github.com/ngxson/smolvlm-realtime-webcam
https://x.com/pocketpal_ai
And check out this real-time camera demo by @ngxson , powered by llama.cpp:
https://github.com/ngxson/smolvlm-realtime-webcam
https://x.com/pocketpal_ai
-
- 3 replies