Open Academic Research on Improving LLaMA to SOTA LLM
active 2023-08-15 → 2025-09-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 771 days from 2023-08-15 to 2025-09-23. Pushes: 4 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 5 total, peak 1 in a day. Comments: 5 total, peak 1 in a day. Stars: 320 total, peak 9 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 |
|---|---|---|---|---|
| AetherCortex | 4 | 4 | 0 | 0 |
| code-x-0018 | 2 | 0 | 0 | 1 |
| zql022 | 1 | 0 | 0 | 0 |
| azhx | 1 | 0 | 0 | 1 |
| RickMeow | 1 | 0 | 0 | 0 |
| anmolagarwal999 | 1 | 0 | 0 | 0 |
| TomLucidor | 1 | 0 | 0 | 1 |
| scorixear | 1 | 0 | 0 | 1 |
| chauncygu | 1 | 0 | 0 | 0 |
| dongguanting | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#34TomLucidor2025-01-09 13:23support llama 3 models
- Issue#34chauncygu2024-07-09 22:39support llama 3 models
- Issue comment#32scorixear2024-01-23 22:04How to fix unstable loss. I am using wizardlm or Llama-X training code with vicuna style chat format for fine-tuning Llama-2-7b-hf model.
- Issue comment#33dongguanting2024-01-10 15:41utils.py and openai==0.8.0 TypeError: 'type' object is not subscriptable
- Issue comment#30azhx2023-11-02 16:57Learning rate fixed at 0 during training via DeepSpeed
- Issue#33zql0222023-10-26 07:20utils.py and openai==0.8.0 TypeError: 'type' object is not subscriptable
- Issue#32code-x-00182023-10-08 16:31How to fix unstable loss. I am using wizardlm or Llama-X training code with vicuna style chat format for fine-tuning Llama-2-7b-hf model.
- Issue comment#30code-x-00182023-09-25 20:15Learning rate fixed at 0 during training via DeepSpeed
- Issue#31RickMeow2023-08-31 07:03About llama-2-70B fine-tuning
- Issue#30anmolagarwal9992023-08-28 11:45Learning rate fixed at 0 during training via DeepSpeed
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 320 stars here means stars gained during the window, not the repo's star count.