4ca7c4be1f
dont consume reader when calculating digest
2023-07-19 00:47:55 -07:00
572fc9099f
add license layers to the parser ( #116 )
2023-07-18 22:49:38 -07:00
68df36ae50
fix pull 0 bytes on completed layer
2023-07-18 19:38:11 -07:00
6e36f948df
Merge pull request #109 from jmorganca/fix-create-memory
...
fix memory leak in create
2023-07-18 17:25:19 -07:00
553fa39fe8
fix memory leak in create
2023-07-18 17:14:17 -07:00
9e15635c2d
attempt two for skipping files in the file walk ( #105 )
2023-07-18 15:37:01 -07:00
9658a5043b
skip files in the list if we can't get the correct model path ( #100 )
2023-07-18 12:39:08 -07:00
f20426a768
fix mkdir blob path
2023-07-18 11:24:19 -07:00
5bea29f610
add new list command ( #97 )
2023-07-18 09:09:45 -07:00
4a28a2f093
add modelpaths ( #96 )
2023-07-17 22:44:21 -07:00
c7dd52271c
remove debugging messages
2023-07-17 14:17:34 -07:00
53d0052c6c
unavoid unnecessary type conversion
2023-07-17 12:35:03 -07:00
28a136e9a3
modelfile params
2023-07-17 12:35:03 -07:00
3862a51a6a
create directories if they do not exist
2023-07-17 11:18:48 -07:00
bcb612a30a
fix file paths for windows
2023-07-17 10:47:47 -07:00
2fb52261ad
basic distribution w/ push/pull ( #78 )
...
* basic distribution w/ push/pull
* add the parser
* add create, pull, and push
* changes to the parser, FROM line, and fix commands
* mkdirp new manifest directories
* make `blobs` directory if it does not exist
* fix go warnings
* add progressbar for model pulls
* move model struct
---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com >
2023-07-16 17:02:22 -07:00
743e957d88
use filepath for os compat
2023-07-14 17:27:14 -07:00
5ade3db040
fix race
...
block on write which only returns when the channel is closed. this is
contrary to the previous arrangement where the handler may return but
the stream hasn't finished writing. it can lead to the client receiving
unexpected responses (since the request has been handled) or worst case
a nil-pointer dereference as the stream tries to flush a nil writer
2023-07-14 15:10:46 -07:00
1775647f76
continue conversation
...
feed responses back into the llm
2023-07-13 17:13:00 -07:00
05e08d2310
return more info in generate response
2023-07-13 09:37:32 -07:00
31590284a7
fix route
2023-07-12 19:21:49 -07:00
2666d3c206
fix pull race
2023-07-12 19:07:23 -07:00
0944b01e7d
pull fixes
2023-07-12 09:55:07 -07:00
a806b03f62
no errgroup
2023-07-11 14:58:10 -07:00
948323fa78
rename partial file
2023-07-11 13:50:26 -07:00
e243329e2e
check api status
2023-07-11 13:42:05 -07:00
2a66a1164a
common stream producer
2023-07-11 13:42:05 -07:00
fd4792ec56
call llama.cpp directly from go
2023-07-11 11:59:18 -07:00
a3ec1ec2a0
consistent error handling for pull and generate
2023-07-10 21:34:15 -07:00
edba935d67
return error in generate response
2023-07-10 13:30:10 -07:00
f5e2e150b8
allow overriding default generate options
2023-07-10 20:58:02 +02:00
74e92d1258
add basic / route for server
2023-07-07 23:46:15 -04:00
f533f85d44
pr feedback
...
- move error check to api client pull
- simplify error check in generate
- return nil on any pull error
2023-07-07 17:12:02 -04:00
61dd87bd90
if directory cannot be resolved, do not fail
2023-07-07 15:27:43 -04:00
b24be8c6b3
update directory url
2023-07-07 15:13:41 -04:00
053739d19f
no prompt on empty line
2023-07-07 11:01:44 -07:00
3f1b7177f2
pass model and predict options
2023-07-07 09:34:05 -07:00
b0618a466e
generate progress
2023-07-06 17:07:40 -07:00
c4b9e84945
progress
2023-07-06 17:07:40 -07:00
15c114decb
fix prompt templates
2023-07-06 17:03:18 -07:00
0637632258
simple pull response
2023-07-06 16:34:44 -04:00
dd960d1d5e
update generate response
2023-07-06 16:34:44 -04:00
d436d51c78
clean up model pull
2023-07-06 16:34:44 -04:00
c9f45abef3
resumable downloads
2023-07-06 16:34:44 -04:00
9b8a456c7d
embed templates
2023-07-06 16:34:44 -04:00
7cf5905063
display pull progress
2023-07-06 16:34:44 -04:00
580fe8951c
free llama model
2023-07-06 16:34:44 -04:00
68e6b4550c
use prompt templates
2023-07-06 16:34:44 -04:00
a6494f8211
pull models
2023-07-06 16:34:44 -04:00
1b7183c5a1
enable metal gpu acceleration
...
ggml-metal.metal must be in the same directory as the ollama binary
otherwise llama.cpp will not be able to find it and load it.
1. go generate llama/llama_metal.go
2. go build .
3. ./ollama serve
2023-07-06 16:34:44 -04:00
