Implements pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), to train and fine-tune the LLaMA2 model to follow human instructions, similar to InstructGPT or ChatGPT, but on a much smaller scale.
active 2023-09-17 → 2026-01-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 850 days from 2023-09-17 to 2026-01-13. Pushes: 15 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 4 in a day. Comments: 3 total, peak 1 in a day. Stars: 52 total, peak 2 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 |
|---|---|---|---|---|
| michaelnny | 22 | 15 | 0 | 3 |
| superclocks | 5 | 0 | 0 | 0 |
| loadingyy | 4 | 0 | 0 | 0 |
| chowkamlee81 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#10loadingyy2024-05-08 08:40bug report
- Issue#9loadingyy2024-05-02 08:32bug report
- Issue#8loadingyy2024-03-27 08:04tokenizer.model?
- Issue comment#8michaelnny2024-03-26 13:51tokenizer.model?
- Issue#8loadingyy2024-03-26 13:40tokenizer.model?
- Issue#7michaelnny2024-02-18 07:02how to do the inference?
- Issue comment#7michaelnny2024-02-18 07:01how to do the inference?
- Issue#7chowkamlee812024-02-10 17:41how to do the inference?
- Issue#6michaelnny2024-01-11 06:07Wrong implementation of gradient accumulation
- Issue#6michaelnny2024-01-10 13:30Wrong implementation of gradient accumulation
- Issue comment#5michaelnny2024-01-02 02:35how to run InstructLLaMA on cpu
- Issue#5michaelnny2024-01-02 02:35how to run InstructLLaMA on cpu
- Issue#5superclocks2024-01-01 02:37how to run InstructLLaMA on cpu
- Issue#4superclocks2024-01-01 02:31how to
- Issue#4superclocks2024-01-01 02:30how to
- Issue#3superclocks2024-01-01 02:30https://github.com/Metaresearch/llama
- Issue#3superclocks2023-12-30 00:48https://github.com/Metaresearch/llama
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 52 stars here means stars gained during the window, not the repo's star count.