baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
2095 commits 1 branch 0 tags 13 MiB
Commit graph

2095 commits

This branch
This branch
All branches
Author SHA1 Message Date
Michael Yang
686f85d6ca
Merge pull request #1132 from jmorganca/mxyng/human-bytes 
replace go-humanize with format.HumanBytes
 2023-11-15 09:46:21 -08:00
bnodnarb
85951d25ef
Created tutorial for running Ollama on NVIDIA Jetson devices (#1098) 2023-11-15 12:32:37 -05:00
Dane Madsen
779e196ef6
Merge branch 'jmorganca:main' into main 2023-11-15 21:38:07 +10:00
Michael Yang
01ea6002c4 replace go-humanize with format.HumanBytes 2023-11-14 14:57:41 -08:00
Jeffrey Morgan
423862042a
treat ollama run model < file as entire prompt, not prompt-per-line (#1126) 
Previously, `ollama run` treated a non-terminal stdin (such as `ollama run model < file`) as containing one prompt per line. To run inference on a multi-line prompt, the only non-API workaround was to run `ollama run` interactively and wrap the prompt in `"""..."""`.

Now, `ollama run` treats a non-terminal stdin as containing a single prompt. For example, if `myprompt.txt` is a multi-line file, then `ollama run model < myprompt.txt` would treat `myprompt.txt`'s entire contents as the prompt.

Co-authored-by: Quinn Slack <quinn@slack.org>
 2023-11-14 16:42:21 -05:00
Bruce MacDonald
df18486c35
Move /generate format to optional parameters (#1127) 
This field is optional and should be under the `Advanced parameters` header
 2023-11-14 16:12:30 -05:00
Jeffrey Morgan
4e612a2e92
use stdout fd for terminal size (#1125) 2023-11-14 16:09:09 -05:00
Matt Williams
47ffb81db7
Update examples/python-json-datagenerator/readme.md 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:33:34 -08:00
Matt Williams
69795d2db0
Update examples/python-json-datagenerator/readme.md 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:33:16 -08:00
Matt Williams
acde0819d9
Update examples/python-json-datagenerator/randomaddresses.py 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:33:02 -08:00
Matt Williams
f748331aa3
Update examples/python-json-datagenerator/predefinedschema.py 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:32:45 -08:00
Matt Williams
f4edc302a8
Update examples/python-loganalysis/readme.md 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:31:22 -08:00
Matt Williams
64b7e0c218
Update examples/python-loganalysis/loganalysis.py 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:31:05 -08:00
Matt Williams
eced0d52ab
Update examples/python-loganalysis/loganalysis.py 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:30:30 -08:00
Matt Williams
96bf9cafa7
Update examples/python-loganalysis/loganalysis.py 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-14 10:30:17 -08:00
Jeffrey Morgan
6e0f686afa --format json should work in interactive mode 2023-11-14 10:22:03 -05:00
Dane Madsen
c1a5220860
Update README.md 2023-11-14 15:31:31 +10:00
Dane Madsen
3b15175a70
Add maid to community integrations 2023-11-14 15:30:03 +10:00
Jeffrey Morgan
c1844bbee2
add json mode to cli (#1095) 2023-11-13 21:54:02 -05:00
Huy Le
cb745965ce
adding ollama.nvim for visibility (#1115) 2023-11-13 17:00:17 -05:00
Enrico Ros
8d29b6a2b6
New big-AGI integration (#1078) 
* New big-AGI integration

Ollama works great in big-AGI, and this document explains how to link the two projects.

* Update README.md
 2023-11-13 16:59:00 -05:00
Ilya Breitburg
724aa64bee
Add Dart library to README.md (#1106) 2023-11-13 14:50:42 -05:00
Michael Yang
d91c103e74
Merge pull request #1055 from dansreis/946-fix-incorrect-base-model-name 
Fixed incorrect base model name
 2023-11-13 08:42:55 -08:00
Kevin Hermawan
98ec7d81e3
Add OllamaKit to the community integrations (#1085) 2023-11-11 14:41:42 -08:00
Matt Williams
b6817a83d8 Add gif and finish readme 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-11-10 16:41:48 -06:00
Matt Williams
73f3448ede add example showing use of JSON format 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-11-10 16:33:56 -06:00
Daniel Reis
7c438f2c53 Replaced method 2023-11-10 20:22:03 +00:00
Daniel Reis
6e46338d44 Reverting previous changes 2023-11-10 20:21:35 +00:00
Jeffrey Morgan
cdddd3df65 add format to example python client 2023-11-10 10:22:21 -08:00
Daniel Hiltgen
afa61bdf45
Merge pull request #1075 from jmorganca/dhiltgen/unexpected-eof 
Resume chunk download on UnexpectedEOF errors
 2023-11-10 08:48:27 -08:00
Daniel Hiltgen
cc54a416c6 Resume chunk download on UnexpectedEOF errors 
If the chunk download is interrupted, resume from where we left off
 2023-11-10 08:29:42 -08:00
Matt Williams
c819d7f68a
Merge pull request #955 from jmorganca/mattw/example-bash-compare 
docs: add examples using bash to compare models
 2023-11-10 08:59:32 -06:00
Matt Williams
e4f59ba073 better streaming plus gif 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-11-10 08:55:17 -06:00
Matt Williams
5de568bffe Add a simple log analysis example 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-11-10 08:28:52 -06:00
Jeffrey Morgan
5cba29b9d6
JSON mode: add `"format" as an api parameter (#1051) 
* add `"format": "json"` as an API parameter
---------
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-09 16:44:02 -08:00
Daniel Reis
d17730356a Removed inline parse model path 2023-11-09 22:44:26 +00:00
Daniel Reis
32d79a6eea Using 'GetShortTagname' method instead 2023-11-09 22:40:37 +00:00
Bruce MacDonald
5b39503bcd
document specifying multiple stop params (#1061) 2023-11-09 13:16:26 -08:00
Bruce MacDonald
1ae84bc2a2
skip gpu if less than 2GB VRAM are available (#1059) 2023-11-09 13:16:16 -08:00
Bruce MacDonald
db8bf336fc
Update README.md 2023-11-09 12:53:24 -08:00
Nick Anderson
d77e094a90
Added gptel to list of integrations (#1062) 2023-11-09 12:52:36 -08:00
Matt Williams
dd3dc47ddb
Merge pull request #992 from aashish2057/aashish2057/langchainjs_doc_update 2023-11-09 05:08:31 -08:00
Michael Yang
c5e1bbabda
instead of static number of parameters for each model family, get the real number from the tensors (#1022) 
* parse tensor info

* refactor decoder

* return actual parameter count

* explicit rounding

* s/Human/HumanNumber/
 2023-11-08 17:55:46 -08:00
Bruce MacDonald
a49d6acc1e
add a complete /generate options example (#1035) 2023-11-08 16:44:36 -08:00
Moritz Poldrack
6e9bcdb9b3
progressbar: make start and end seamless (#1042) 2023-11-08 16:42:40 -08:00
Matt Williams
13086363bd Update as per bmacd 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-11-08 18:09:05 -06:00
Bruce MacDonald
ec2a31e9b3
support raw generation requests (#952) 
- add the optional `raw` generate request parameter to bypass prompt formatting and response context
-add raw request to docs
 2023-11-08 14:05:02 -08:00
Amith Koujalgi
ec84c02d54
Add Ollama4j Java library to the list of community libraries (#1044) 2023-11-08 11:04:32 -08:00
Kevin Hermawan
2a88b66bc9
Add Ollamac to community integrations (#1043) 2023-11-08 11:01:09 -08:00
Jeffrey Morgan
2d0faea96c clean up README.md 2023-11-08 00:03:29 -08:00