| Branch | Commit message | Author | Age | |
|---|---|---|---|---|
| master | Use WizardLM instead of Vicuna | Anthony Wang | 2 years | |
| Age | Commit message | Author | ||
| 2023-05-30 | Use WizardLM instead of VicunaHEADmaster | Anthony Wang | ||
| 2023-05-29 | Update README | Anthony Wang | ||
| 2023-05-29 | Hide stderr output | Anthony Wang | ||
| 2023-05-29 | Use GPU acceleration for llama.py | Anthony Wang | ||
| 2023-04-10 | Fix bug | Anthony Wang | ||
| 2023-04-10 | Stop after 1024 tokens | Anthony Wang | ||
| 2023-04-10 | Don't generate infinitely | Anthony Wang | ||
| 2023-04-10 | Finally! | Anthony Wang | ||
| 2023-04-10 | Return 204 on favicon.ico request, pad prompt with "### Human:", "### Assista... | Anthony Wang | ||
| 2023-04-10 | Fix typo | Anthony Wang | ||
| [...] | ||||
| Clone | ||||
| https://git.unnamed.website/textgen | ||||
 |
index : textgen | |
| A simple llama.cpp web API | Anthony Wang |
| aboutsummaryrefslogtreecommitdiff |