This is a public Repository to manage the Machine Learning Project for WS 2024/25.
active 2024-10-28 → 2025-03-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 141 days from 2024-10-28 to 2025-03-17. Pushes: 77 total, peak 8 in a day. Pull requests: 3 total, peak 2 in a day. Issues: 62 total, peak 9 in a day. Comments: 18 total, peak 5 in a day. Stars: 1 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| mhueppe | 132 | 62 | 0 | 18 |
| dasjannishuh | 17 | 12 | 3 | 0 |
| nllink | 11 | 3 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#34dasjannishuh2025-03-15 12:15CHAT GPT style GUI update
- Issue#26mhueppe2025-01-28 19:35Avoid Repeated words during inference
- Issue#33mhueppe2025-01-28 19:29Visualize the Attention scores in a different matter
- Issue#31mhueppe2025-01-28 19:29Add Evaluation Metrics to Decoder-Only Training and Weights & Biases Dashboard
- Issue#28mhueppe2025-01-28 19:29Titel to Abstract Model
- Issue#34mhueppe2025-01-22 14:22CHAT GPT style GUI update
- Issue comment#33mhueppe2025-01-17 09:39Visualize the Attention scores in a different matter
- Issue comment#33mhueppe2025-01-16 15:52Visualize the Attention scores in a different matter
- Issue#17mhueppe2025-01-16 14:20Look into different model Architecture
- Issue#15mhueppe2025-01-16 14:20Hyperparameter tuning optimizing for smaller Model size and masked accuracy
- Issue#25mhueppe2025-01-16 14:20Implement dynamic loading and data preprocessing for complete Arxiv dataset
- Issue#23mhueppe2025-01-16 14:20Implement more Evaluation Metrics
- Issue#29mhueppe2025-01-16 14:19Train different model sizes
- Issue#27mhueppe2025-01-16 14:19Implement likelihood based inference.
- Issue#33mhueppe2025-01-16 14:19Visualize the Attention scores in a different matter
- Issue comment#32mhueppe2025-01-16 14:10Receive And Plot Attention Scores for input and output
- Issue#32mhueppe2025-01-16 14:10Receive And Plot Attention Scores for input and output
- Issue#32mhueppe2025-01-16 13:45Receive And Plot Attention Scores for input and output
- Issue#31nllink2025-01-11 20:08Add Evaluation Metrics to Decoder-Only Training and Weights & Biases Dashboard
- Issue#24nllink2025-01-11 20:03Create decoder-only Transformer
- Issue#23mhueppe2025-01-08 13:48Implement more Evaluation Metrics
- Issue#30mhueppe2025-01-06 17:14Examine Easy data points
- Issue comment#30mhueppe2025-01-06 17:13Examine Easy data points
- Issue#30mhueppe2025-01-06 13:31Examine Easy data points
- Issue#29mhueppe2025-01-06 12:50Train different model sizes
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.