f8ff2d6879
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
2023-07-05 18:11:12 -07:00
63d17c6f64
Go
2023-07-05 16:32:49 -04:00
52ac534889
remove debug print statements
2023-07-05 16:29:12 -04:00
ec4f76844d
fix crash in bindings
2023-07-05 16:28:18 -04:00
37ffcb48b5
Merge branch 'jmorganca/engine' of github.com:jmorganca/ollama into jmorganca/engine
2023-07-05 15:38:04 -04:00
328c06eb14
separate routes
2023-07-05 15:37:49 -04:00
bf75b3559c
updated readme
2023-07-05 15:37:33 -04:00
cdfd056d68
add binary to .gitignore
2023-07-05 15:36:34 -04:00
0389affa07
wip
2023-07-04 16:06:04 -04:00
79ebc5c5a1
wip
2023-07-04 00:47:00 -04:00
b9b07f1a97
update `Dockerfile`
2023-07-03 18:56:17 -04:00
7806512eff
fix llama.cpp build
2023-07-03 18:56:10 -04:00
a3ce37e7da
move prompt templates out of python bindings
2023-07-03 17:14:20 -04:00
7c257434fc
add llama.cpp go bindings
2023-07-03 16:32:48 -04:00
3432181e3e
wip go engine
...
Co-authored-by: Patrick Devine <pdevine@sonic.net>
2023-07-03 15:22:44 -04:00
35f202f573
use app router
2023-07-02 22:05:26 -04:00
0efa1f9fb2
format `models.json`
2023-07-02 20:33:23 -04:00
d972647e7c
simple website
2023-07-02 19:52:40 -04:00
8685a5ad18
move .prettierrc.json to root
2023-07-02 17:34:46 -04:00
3cd59936a2
move `desktop` -> `app`
2023-07-02 17:26:55 -04:00
55898a3382
Move python docs to separate file
2023-07-01 17:54:29 -04:00
0d2f41e9a4
remove unused `build.py`
2023-07-01 13:48:36 -04:00
1dd3282f08
update `desktop/README.md`
2023-07-01 13:45:59 -04:00
23c589d578
output confirmation after pull
2023-06-30 16:40:28 -04:00
4c8c61c9cf
Update README.md
2023-06-30 16:30:35 -04:00
f1d5036f1e
v0.0.9
2023-06-30 16:28:20 -04:00
d01be075b6
search command
2023-06-30 16:27:47 -04:00
fd1207a44b
bump version to `0.0.8`
2023-06-30 16:05:14 -04:00
76918ddb67
change name.json
2023-06-30 15:15:18 -04:00
9e5dfc66a3
Merge pull request #29 from jmorganca/pull-model-name
...
Pull model name
2023-06-30 11:58:58 -07:00
76fb9eea1e
use Path / operator
2023-06-30 11:57:28 -07:00
3ce3caaf65
fix pull model name
2023-06-30 11:57:28 -07:00
3c5a543642
bump version to `0.0.7`
2023-06-30 14:54:29 -04:00
cc329b3dd8
Merge pull request #20 from jmorganca/close-matches
...
use difflib.get_close_matches
2023-06-30 11:54:07 -07:00
ba3cbbbb4c
use difflib.get_close_matches
2023-06-30 11:53:14 -07:00
e69a08f1b1
Merge pull request #17 from jmorganca/ctransformers
...
use ctransformers as backup to llama.cpp
2023-06-30 11:46:13 -07:00
07d8d56177
use all caps for constants
2023-06-30 10:36:10 -07:00
9dfef44a54
Update models.json format
2023-06-30 13:33:05 -04:00
4d0eb7639a
use ctransformers as backup to llama-cpp
2023-06-30 10:33:01 -07:00
5cea13ce00
rename model to model_name to avoid collision
2023-06-30 10:33:01 -07:00
af66c5695a
Update with some examples
2023-06-30 13:08:46 -04:00
efba500dd6
better `README.md` install instructions
2023-06-30 12:39:25 -04:00
56922cfd3d
fix desktop `README.md` until download links are ready
2023-06-30 12:34:32 -04:00
bbc05f957f
add `docker` instruction
2023-06-30 12:31:00 -04:00
48920c873b
add basic `Dockerfile`
2023-06-30 12:19:04 -04:00
05092f61a6
Update note in `README.md`
2023-06-30 12:19:04 -04:00
ab49a18a33
add help and descriptions to cli
2023-06-30 12:14:59 -04:00
36168300d9
update commands
...
- change list to models
- remove generate from cli in favour of run
2023-06-30 11:42:35 -04:00
e0ccc0c1b7
change pulled remote file name to lower case
2023-06-30 11:40:00 -04:00
a11cddbf99
remove models home param
2023-06-30 11:37:12 -04:00
Michael Yang
Jeffrey Morgan
Bruce MacDonald
Michael Chiang
Michael Yang