- 07 Dec, 2023 1 commit
-
-
Jeffrey Morgan authored
-
- 06 Dec, 2023 14 commits
-
-
Matt Williams authored
Simple chat example
-
Matt Williams authored
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Bruce MacDonald authored
-
Matt Williams authored
Co-authored-by:Bruce MacDonald <brucewmacdonald@gmail.com>
-
Matt Williams authored
Co-authored-by:Bruce MacDonald <brucewmacdonald@gmail.com>
-
Matt Williams authored
Co-authored-by:Bruce MacDonald <brucewmacdonald@gmail.com>
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Xe Iaso authored
Signed-off-by:Xe Iaso <xe@camellia.finch-kitefin.ts.net>
-
Michael Yang authored
do not fail on unsupported template variables
-
Michael Yang authored
add version api and show server version in cli
-
Samuel Calderon authored
Thank you @calderonsamuel
-
Michael Yang authored
update for qwen
-
Jeffrey Morgan authored
-
- 05 Dec, 2023 25 commits
-
-
Bruce MacDonald authored
-
Michael Yang authored
load projectors
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
split from into one or more models
-
Michael Yang authored
refactor layer creation
-
Michael Yang authored
fix: trim space in modelfile fields
-
Bruce MacDonald authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Jeffrey Morgan authored
This reverts commit 7a0899d6.
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
previous layer creation was not ideal because: 1. it required reading the input file multiple times, once to calculate the sha256 checksum, another to write it to disk, and potentially one more to decode the underlying gguf 2. used io.ReadSeeker which is prone to user error. if the file isn't reset correctly or in the right place, it could end up reading an empty file there are also some brittleness when reading existing layers else writing the inherited layers will error reading an already closed file this commit aims to fix these issues by restructuring layer creation. 1. it will now write the layer to a temporary file as well as the hash function and move it to the final location on Commit 2. layers are read once once when copied to the destination. exception is raw model files which still requires a second read to decode the model metadata
-
Michael Yang authored
-
Michael Yang authored
-