What does it do?
NeuronDump reads GGUF model files (the format used by Ollama and llama.cpp) and shows their layers, attention heads, vocabulary, chat template, and weight statistics. [1] It can remove unused parts and write a smaller GGUF that still runs in Ollama and llama.cpp. [2] With the trace feature, it can run supported models on the CPU so a user can follow a token through every layer, edit the model live, and bake the edits into a new GGUF. [3]
Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
| Package | Version | Downloads · 30d | Trend · 30d |
|---|---|---|---|
neurondumpv0.1.4 | v0.1.4 | — | — |
neurondump-cliv0.1.4 | v0.1.4 | — | — |
neurondump-corev0.1.4 | v0.1.4 | — | — |
neurondump-ggufv0.1.4 | v0.1.4 | — | — |
neurondump-tracev0.1.4 | v0.1.4 | — | — |
| — | — | — | |
neurondump-webv0.1.4 | v0.1.4 | — | — |
neurondumpv0.1.4 | v0.1.4 | ≥302 | |
wamr3dv0.9.4 | v0.9.4 | ≥1K |
Live mentions badge
Show how many posts mention your project in the last 30 days.
