Huashu Design
alchaincyf · Skill
Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…
Shows daily download history, likes and derivative families for every model on the Hugging Face Hub since July 2024, with comparison charts and weekly rankings. It suits model authors and analysts who follow open models.
Model Pulse by emanforhelp is a kit in the Research category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.
pip install -U huggingface_hub hf download emanforhelp/model-pulse --repo-type space --local-dir model-pulse cd model-pulse
Model Pulse is a static page that charts how often each Hugging Face Hub model is downloaded and liked, day by day since July 2024, and which families of derived models it has. Pick a model to read its history, set up to five side by side, and check what share of its use comes from variants made from it. It is an independent project and not affiliated with Hugging Face.
It suits model authors, analysts and curious readers who want to see how open models are used over time.
| Industry | Who uses it | How they use it | Example |
|---|---|---|---|
| AI research | Analysts | Track downloads and growth of open models over time | An analyst compares up to five models on one chart. |
| Model publishing | Model authors | See how much of their reach comes from quantizations, fine-tunes, adapters and merges | An author looks up their model and its derivative family. |
| Community | Hub contributors | Review an author's last 12 months in six cards | A contributor opens the Wrapped view for their own account. |
| Journalism | Tech writers | Find the weekly most downloaded and fastest growing models | A writer reads the weekly rankings for a news piece. |
If you need data from outside the Hugging Face Hub, skip it, because it covers only models there.
| Use case | Who | What they get back |
|---|---|---|
| Look up a model | Anyone | Daily download history and likes for that model |
| Compare models | Analysts | Up to five models on one chart |
| See weekly rankings | Writers and authors | Top downloads, quickest risers, fresh breakouts, big families and leading organizations |
pip install -U huggingface_hub hf download emanforhelp/model-pulse --repo-type space --local-dir model-pulse cd model-pulse
Open the page and use the controls, or add a query to the page link. A model query opens that model directly, the galaxy view draws all models built on a base model, and the wrapped view shows an author's year.
?model=org/name ?view=galaxy ?view=wrapped
| Tool | What it does |
|---|---|
| Model lookup | Shows one model's daily downloads, likes and derivative families |
| Compare | Puts up to five models on one chart |
| Galaxy | Draws every model built on a base model as a galaxy |
| Wrapped | Shows an author's last 12 months in six cards |
| Weekly rankings | Lists top downloads, quickest risers, fresh breakouts, big families and leading organizations |
| README badge | Shows monthly downloads with a sparkline, updated daily |
You look up a model by adding its organization and name to the model query. The page shows its daily downloads and likes, and how much of its reach comes from quantizations, fine-tunes, adapters and merges.
If you are new, open the page and look up a model you already know. Then try the galaxy view to see the family that grew from it.
If you know the field, the data comes from daily snapshots of the Hub's own stats, compiled into a separate dataset. The page counts derivatives by kind, so you can separate quantizations from fine-tunes, adapters and merges.
Shows daily download history, likes and derivative families for every model on the Hugging Face Hub since July 2024, with comparison charts and weekly rankings. It suits model authors and analysts who follow open models.
Made by emanforhelp on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.
What it is: Model Pulse is a static page that charts how often each Hugging Face Hub model is downloaded and liked, day by day since July 2024, and which families of derived models it has. Pick a model to read its history, set up to five side by side, and check what share of its use comes from variants made from it. It is an independent project and not affiliated with Hugging Face.
Who it suits: It suits model authors, analysts and curious readers who want to see how open models are used over time.
Industry | Who uses it | How they use it | Example
AI research | Analysts | Track downloads and growth of open models over time | An analyst compares up to five models on one chart.
Model publishing | Model authors | See how much of their reach comes from quantizations, fine-tunes, adapters and merges | An author looks up their model and its derivative family.
Community | Hub contributors | Review an author's last 12 months in six cards | A contributor opens the Wrapped view for their own account.
Journalism | Tech writers | Find the weekly most downloaded and fastest growing models | A writer reads the weekly rankings for a news piece.
If you need data from outside the Hugging Face Hub, skip it, because it covers only models there.
Where to use it:
Use case | Who | What they get back
Look up a model | Anyone | Daily download history and likes for that model
Compare models | Analysts | Up to five models on one chart
See weekly rankings | Writers and authors | Top downloads, quickest risers, fresh breakouts, big families and leading organizations
How to set it up:
pip install -U huggingface_hub
hf download emanforhelp/model-pulse --repo-type space --local-dir model-pulse
cd model-pulse
How to use it: Open the page and use the controls, or add a query to the page link. A model query opens that model directly, the galaxy view draws all models built on a base model, and the wrapped view shows an author's year.
?model=org/name
?view=galaxy
?view=wrapped
Tool | What it does
Model lookup | Shows one model's daily downloads, likes and derivative families
Compare | Puts up to five models on one chart
Galaxy | Draws every model built on a base model as a galaxy
Wrapped | Shows an author's last 12 months in six cards
Weekly rankings | Lists top downloads, quickest risers, fresh breakouts, big families and leading organizations
README badge | Shows monthly downloads with a sparkline, updated daily
Example: You look up a model by adding its organization and name to the model query. The page shows its daily downloads and likes, and how much of its reach comes from quantizations, fine-tunes, adapters and merges.
For newcomers and experts: If you are new, open the page and look up a model you already know. Then try the galaxy view to see the family that grew from it.
If you know the field, the data comes from daily snapshots of the Hub's own stats, compiled into a separate dataset. The page counts derivatives by kind, so you can separate quantizations from fine-tunes, adapters and merges.
Daily snapshots of Hub stats
Compiled into a dataset
The page reads the history
Charts, rankings and badges appear
Good to know:
Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.
README.md 5 KB
Listed Hugging Face Spaces in the same category that share the most tags with this one.
| Product | Likes | Built with | License | Last change |
|---|---|---|---|---|
| Model Pulse by emanforhelp This page | 7 | static | apache-2.0 | |
| Model PulseShares analytics · data-visualization · downloads | 214 | static | apache-2.0 | |
| Paper PulseShares statistics · leaderboard · static | 27 | static | apache-2.0 | |
| Arena LeaderboardShares leaderboard · static | 5,039 | static | apache-2.0 | |
| MTEB-BR LeaderboardShares leaderboard · static | 126 | static | apache-2.0 | |
| Icelandic LLM LeaderboardShares leaderboard · static | 20 | static | cc-by-4.0 |
alchaincyf · Skill
Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…
op7418 · Skill
Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…
alirezarezvani · Skill
Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…
dBenf · Kit
Answers typed questions about satellite image patches from all 12 Sentinel-2 bands, returning a probability for each option without writing text. A Qwen3.5-0.8…
zimmerk4 · Kit
Plays the full game Getting Over It from the bottom to the end with a small trained policy network that learned inside a JAX physics simulator. For reinforceme…
yuji-nozawa · Kit
Pretrained vision transformer checkpoints in three sizes from a research paper on training attention heads to focus on image regions. For researchers who extra…