 Jeffrey Morgan
|
949fc4eafa
wip `/api/chat`
|
1 سال پیش |
 Jay Nakrani
|
1d0ebe67e8
Document response stream chunk delimiter. (#632)
|
1 سال پیش |
 Bruce MacDonald
|
a1b2d95f96
remove unused push/pull params (#650)
|
1 سال پیش |
 Michael Yang
|
8608eb4760
prune empty directories
|
1 سال پیش |
|
Jeffrey Morgan
|
9b12a511ca
check other request fields before load short circuit in `/api/generate`
|
1 سال پیش |
|
Bruce MacDonald
|
5d71bda478
close llm on interrupt (#577)
|
1 سال پیش |
|
Michael Yang
|
82f5b66c01
register HEAD /api/tags
|
1 سال پیش |
|
Michael Yang
|
c986694367
fix HEAD / request
|
1 سال پیش |
|
Bruce MacDonald
|
4cba75efc5
remove tmp directories created by previous servers (#559)
|
1 سال پیش |
|
Michael Yang
|
1fabba474b
refactor default allow origins
|
1 سال پیش |
|
Bruce MacDonald
|
1255bc9b45
only package 11.8 runner
|
1 سال پیش |
 Patrick Devine
|
80dd44e80a
Cmd changes (#541)
|
1 سال پیش |
|
Bruce MacDonald
|
f221637053
first pass at linux gpu support (#454)
|
1 سال پیش |
|
Patrick Devine
|
e7e91cd71c
add autoprune to remove unused layers (#491)
|
1 سال پیش |
|
Patrick Devine
|
790d24eb7b
add show command (#474)
|
1 سال پیش |
|
Michael Yang
|
681f3c4c42
fix num_keep
|
1 سال پیش |
|
Michael Yang
|
eeb40a672c
fix list models for windows
|
1 سال پیش |
|
Michael Yang
|
0f541a0367
s/ListResponseModel/ModelResponse/
|
1 سال پیش |
|
Bruce MacDonald
|
42998d797d
subprocess llama.cpp server (#401)
|
1 سال پیش |
|
Patrick Devine
|
8bbff2df98
add model IDs (#439)
|
1 سال پیش |
|
Michael Yang
|
95187d7e1e
build release mode
|
1 سال پیش |
|
Jeffrey Morgan
|
a9f6c56652
fix `FROM` instruction erroring when referring to a file
|
1 سال پیش |
 Ryan Baker
|
0a892419ad
Strip protocol from model path (#377)
|
1 سال پیش |
|
Bruce MacDonald
|
326de48930
use loaded llm for embeddings
|
1 سال پیش |
|
Patrick Devine
|
d9cf18e28d
add maximum retries when pushing (#334)
|
1 سال پیش |
|
Michael Yang
|
6517bcc53c
Merge pull request #290 from jmorganca/add-adapter-layers
|
1 سال پیش |
|
Michael Yang
|
6a6828bddf
Merge pull request #167 from jmorganca/decode-ggml
|
1 سال پیش |
|
Jeffrey Morgan
|
040a5b9750
clean up cli flags
|
1 سال پیش |
|
Michael Yang
|
6de5d032e1
implement loading ggml lora adapters through the modelfile
|
1 سال پیش |
|
Michael Yang
|
fccf8d179f
partial decode ggml bin for more info
|
1 سال پیش |
