COMMITS
/ llama_cpp/_internals.py June 19, 2024
A
fix: Make destructor to automatically call .close() method on Llama class.
Andrei Betlen committed
June 13, 2024
J
feat: Add `.close()` method to `Llama` class to explicitly free model from memory (#1513)
Junpei Kawamoto committed
S
feat: Support SPM infill (#1492)
Sigbjørn Skjæret committed
June 7, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
June 4, 2024
S
fix: Avoid duplicate special tokens in chat formats (#1439)
Sigbjørn Skjæret committed
June 1, 2024
A
fix: Use numpy recarray for candidates data, fixes bug with temp < 0
Andrei Betlen committed
May 4, 2024
April 30, 2024
April 26, 2024
D
feat: Allow for possibly non-pooled embeddings (#1380)
Douglas Hanley committed
April 22, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
April 1, 2024
Y
fix: last tokens passing to sample_repetition_penalties function (#1295)
Yuri Mikhailov committed
February 28, 2024
A
fix: Remove deprecated cfg sampling functions
Andrei Betlen committed
February 26, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
February 23, 2024
A
misc: use typesafe byref for internal classes
Andrei Betlen committed
February 22, 2024
A
fix: Raise exceptions when llama model or context fails to load
Andrei Betlen committed
February 21, 2024
February 14, 2024
D
feat: Support batch embeddings (#1186)
Douglas Hanley committed
A
fix: destructor exception where internal classes are missing some uninitialized attributes
Andrei Betlen committed
February 6, 2024
A
fix: Use llama_log_callback to avoid suppress_stdout_stderr
Andrei Betlen committed
January 29, 2024
A
Automatically set chat format from gguf (#1110)
Andrei committed
January 19, 2024
A
feat: Expose gguf model metadata in metadata property
Andrei Betlen committed
January 17, 2024
A
Move helper classes to _internals submodule
Andrei Betlen committed