| Age | Commit message (Expand) | Author |
|---|---|---|
| 2024-05-30 | Move convert.py to examples/convert-legacy-llama.py (#7430) | Galunid |
| 2024-05-08 | convert-hf : save memory with lazy evaluation (#7075) | compilade |
| 2024-05-03 | convert.py : add python logging instead of print() (#6511) | Brian |
| 2024-04-18 | convert : support models with multiple chat templates (#6588) | Sigbjørn Skjæret |
| 2024-02-15 | fix(gguf-py): special tokens are no longer skipped when add_<token>_token is ... | Michaël de Vries |
| 2023-12-21 | py : open merges file as 'utf-8' (#4566) | howlger |
| 2023-12-17 | gguf-py : fail fast on nonsensical special token IDs (#4489) | Jared Van Bortel |
| 2023-11-19 | gguf-py : export chat templates (#4125) | slaren |
| 2023-11-16 | Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040) | Kerfuffle |
| 2023-11-11 | gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) | Kerfuffle |
 |
index : ik_llama.cpp.git | |
| Unnamed repository; edit this file 'description' to name the repository. |
| summaryrefslogtreecommitdiff |