Don Mahurin
Don Mahurin
fix klaatu compile
This change only outputs the completed lines to the text file, the lines that are later overwritten are not output. This allows stream to be better used for dictation.
Would the project accept a PR for providing directly supported python bindings. I know the README mentions llama-cpp-python. And there are these and perhaps others... pip install llama-cpp-python pip install...
Background/rationale: This pull request addresses #82 and #1156, bringing the low level python ctypes binding into llama.cpp. This should hopefully help reduce python binding fragmentation, and help broaden llama.cpp development....
remove obsolete parts. update package dependencies.
Llama code now runs on Codon. (with a 74 X improvement compared to Python). https://github.com/dmahurin/llama2.codon/ https://github.com/tairov/llama2.py/pull/5 But, to get this to work changes/hacks were needed to support using 'struct' to...
The example (in the README) worked and macos (M2) with JAX backend and versions including 1.2.4, but stopped working with versions 2.x.x, including with 2.1.2. The failure for all current...
These changes add support for training with tinyshakesphere (change from llama2.py), and simple blank line separated text.