Commit graph

1553 commits

Author SHA1 Message Date
Michael Yang
5b84404c64 handle concurrent requests for the same blobs 2023-10-06 12:56:43 -07:00
Michael Yang
8544edca21 parallel chunked downloads 2023-10-06 12:56:43 -07:00
Bruce MacDonald
5d22319a2c
rename server subprocess (#700)
- this makes it easier to see that the subprocess is associated with ollama
2023-10-06 10:15:42 -04:00
Bruce MacDonald
2130c0708b
output type parsed from modelfile (#678) 2023-10-05 14:58:04 -04:00
Patrick Devine
61ff1946e6
revise help text (#706) 2023-10-05 11:36:07 -07:00
Bruce MacDonald
d06bc0cb6e
enable q8, q5, 5_1, and f32 for linux gpu (#699) 2023-10-05 12:53:47 -04:00
Alexander F. Rødseth
d104b7e997
Fix go test./... issue: fmt.Println arg list ends with redundant newline (#705) 2023-10-05 11:11:04 -04:00
Bruce MacDonald
9e2de1bd2c
increase streaming buffer size (#692) 2023-10-04 14:09:00 -04:00
Jeffrey Morgan
dc87e9c9ae update Dockerfile to pass GOFLAGS 2023-10-03 07:05:15 -07:00
Michael Yang
367cb68dc1
Merge pull request #686 from jmorganca/mxyng/starcoder
decode starcoder
2023-10-02 22:47:19 -07:00
Michael Yang
c02c0cd483 starcoder 2023-10-02 19:56:51 -07:00
Patrick Devine
1852755154
show a default message when license/parameters/system prompt/template aren't specified (#681) 2023-10-02 14:34:52 -07:00
James Braza
6f2ce74231 Got rif of all caps to show it can be lower case 2023-10-02 13:54:27 -07:00
James Braza
6edcc5c79f Using code highlighting syntax around Modelfile 2023-10-02 13:46:05 -07:00
Bruce MacDonald
b1f7123301
clean up num_gpu calculation code (#673) 2023-10-02 14:53:42 -04:00
Bruce MacDonald
1fbf3585d6
Relay default values to llama runner (#672)
* include seed in params for llama.cpp server and remove empty filter for temp

* relay default predict options to llama.cpp

- reorganize options to match predict request for readability

* omit empty stop

---------

Co-authored-by: hallh <hallh@users.noreply.github.com>
2023-10-02 14:53:16 -04:00
Patrick Devine
99d5161e8a
don't wordwrap when stdout is redirected or piped (#662) 2023-10-02 11:50:55 -07:00
Michael
ea8380be45
add community project: Chatbot Ollama
add community project: Chatbot Ollama by @ivanfioravanti
2023-10-02 09:04:31 -07:00
Jeffrey Morgan
4f25092dc1 fix build_docker.sh permissions 2023-10-01 16:42:32 -07:00
Jiayu Liu
4fc10acce9
add some missing code directives in docs (#664) 2023-10-01 11:51:01 -07:00
Michael Yang
0a4f21c0a7
fix docker build (#659) 2023-09-30 13:34:01 -07:00
Jeffrey Morgan
9abb66254a docker: fix volume permission errors 2023-09-30 12:32:15 -07:00
Jay Nakrani
1d0ebe67e8
Document response stream chunk delimiter. (#632)
Document response stream chunk delimiter.
2023-09-29 21:45:52 -07:00
Bruce MacDonald
a1b2d95f96
remove unused push/pull params (#650) 2023-09-29 17:27:19 -04:00
Michael Yang
c0b1bf7537
Merge pull request #606 from jmorganca/mxyng/install.sh-2
ordered list of install locations
2023-09-29 11:30:46 -07:00
Michael Yang
cdfeb165ca
Merge pull request #608 from jmorganca/mxyng/build
update build scripts
2023-09-29 11:30:25 -07:00
Michael Yang
92d454ec5f update build_darwin.sh 2023-09-29 11:29:23 -07:00
Michael Yang
9333b0cc82
Merge pull request #612 from jmorganca/mxyng/prune-empty-directories
prune empty directories
2023-09-29 11:23:39 -07:00
Bruce MacDonald
9771b1ec51
windows runner fixes (#637) 2023-09-29 11:47:55 -04:00
Patrick Devine
76db4a49cf
allow the user to cancel generating with ctrl-C (#641) 2023-09-28 17:13:01 -07:00
Luc Stepniewski
4aa0976a2e
Added missing return preventing SIGSEGV because of missing resp (#621)
Co-authored-by: Luc Stepniewski <luc@eclipse-fr.com>
2023-09-28 14:25:22 -07:00
Patrick Devine
92c20fdae6
fix error messages for unknown commands in the repl (#611) 2023-09-28 14:19:45 -07:00
Michael Yang
c951da7096
Merge pull request #634 from jmorganca/mxyng/int64
use int64 consistently
2023-09-28 14:17:47 -07:00
Bruce MacDonald
24d82a23a2
do not download updates multiple times (#633) 2023-09-28 15:29:17 -04:00
Michael Yang
f40b3de758 use int64 consistently 2023-09-28 11:07:24 -07:00
Michael
5f4008c296
Update README.md
adding in instruction to run mistral
2023-09-28 09:06:03 -07:00
Aaron Coffey
6ae33d8141
Update modelfile.md to reflect the usage of num_gpu. (#629) 2023-09-28 10:21:21 -04:00
Jeffrey Morgan
c5664c1fef
Update faq.md 2023-09-27 13:49:43 -07:00
Bruce MacDonald
958a5a8184 revert fedora cuda version check 2023-09-27 15:12:29 -04:00
Michael Yang
8608eb4760 prune empty directories 2023-09-27 10:58:09 -07:00
Bruce MacDonald
a2b210130f
fedora install fixes (#609) 2023-09-27 11:43:47 -04:00
Bruce MacDonald
ed20837f9a Update modelfile.md 2023-09-27 10:38:10 -04:00
James Braza
1db2a61dd0
Added num_predict to the options table (#614) 2023-09-27 10:26:08 -04:00
Jeffrey Morgan
2ded8ab206 use 11.8.0 nvidia dockerfile base image for now 2023-09-26 21:48:41 -07:00
Michael Yang
e6b3648bbf
Merge pull request #616 from jmorganca/mxyng/fix-model-name 2023-09-26 20:54:18 -07:00
Michael Yang
0625e805f0 fix model name not matching 2023-09-26 19:50:04 -07:00
Michael Yang
c38ec5befb
Merge pull request #598 from jmorganca/mxyng/help-exit
add painter message for exit
2023-09-26 15:17:40 -07:00
Michael Yang
c577721a43
Merge pull request #605 from jmorganca/mxyng/install.sh
do not unload nouveau driver
2023-09-26 09:53:05 -07:00
Michael Yang
29c056ea39 ordered list of install locations 2023-09-26 09:38:11 -07:00
Michael Yang
9fc3bba9cf do no unload nouveau driver 2023-09-26 09:36:54 -07:00