llama.cpp
11ac9800 - llama : improve infill support and special token detection (#9798)

Commit

261 days ago

llama : improve infill support and special token detection (#9798) * llama : improve infill support ggml-ci * llama : add more FIM token strings ggml-ci * server : update prompt on slot restore (#9800) * gguf : deprecate old FIM token KVs

References

#9798 - llama : improve infill support and special token detection

Author

ggerganov

Parents

943d20b4

Files12

common
- arg.cpp
- common.cpp
- common.h
examples
- infill
  - infill.cpp
- server
  - README.md
  - server.cpp
gguf-py/gguf
- constants.py
- gguf_writer.py
include
- llama.h
src
- llama-vocab.cpp
- llama-vocab.h
- llama.cpp

llama.cpp 11ac9800 - llama : improve infill support and special token detection (#9798)

llama.cpp
11ac9800 - llama : improve infill support and special token detection (#9798)