fb6cbc02fb
update named templates
2024-07-05 16:29:32 -07:00
9b6c2e6eb6
detect chat template from KV
2024-06-06 16:03:47 -07:00
171eb040fc
simplify safetensors reading
2024-05-21 11:28:22 -07:00
34d5ef29b3
fix conversion for f16 or f32 inputs
2024-05-21 11:28:22 -07:00
63a453554d
go mod tidy
2024-05-19 23:03:57 -07:00
1e1634daca
update go deps ( #4324 )
2024-05-10 21:39:27 -07:00
9f8691c6c8
Add llama2 / torch models for ollama create ( #3607 )
2024-04-15 11:26:42 -07:00
5a5efee46b
Add gemma safetensors conversion ( #3250 )
...
Co-authored-by: Michael Yang <mxyng@pm.me >
2024-03-28 18:54:01 -07:00
1b272d5bcd
change github.com/jmorganca/ollama to github.com/ollama/ollama ( #3347 )
2024-03-26 13:04:17 -07:00
2c017ca441
Convert Safetensors to an Ollama model ( #2824 )
2024-03-06 21:01:51 -08:00
fc483274ad
clean up go.mod
2024-02-23 16:53:36 -08:00
66ef308abd
Import "containerd/console" lib to support colorful output in Windows terminal
2024-02-15 05:56:45 +00:00
29e90cc13b
Implement new Go based Desktop app
...
This focuses on Windows first, but coudl be used for Mac
and possibly linux in the future.
2024-02-15 05:56:45 +00:00
ecbfc0182f
Go bump to v1.21 to pick up slog
2024-01-18 14:12:57 -08:00
39928a42e8
Always dynamically load the llm server library
...
This switches darwin to dynamic loading, and refactors the code now that no
static linking of the library is used on any platform
2024-01-11 08:42:47 -08:00
d4cd695759
Add cgo implementation for llama.cpp
...
Run the server.cpp directly inside the Go runtime via cgo
while retaining the LLM Go abstractions.
2023-12-19 09:05:46 -08:00
630518f0d9
Add unit test of API routes ( #1528 )
2023-12-14 16:47:40 -08:00
7232f1fa41
go mod tidy
2023-12-04 16:59:23 -08:00
01ea6002c4
replace go-humanize with format.HumanBytes
2023-11-14 14:57:41 -08:00
341fb7e35f
go mod tidy
2023-11-01 11:54:25 -07:00
deeac961bb
new readline library ( #847 )
2023-10-25 16:41:18 -07:00
bb8464c0d2
update golang.org/x/net fixes CVE-2023-3978,CVE-2023-39325,CVE-2023-44487 ( #855 )
2023-10-25 16:17:24 -07:00
a0c3e989de
deprecate modelfile embed command ( #759 )
2023-10-16 11:07:37 -04:00
8544edca21
parallel chunked downloads
2023-10-06 12:56:43 -07:00
87d9efb364
switch to forked readline lib which doesn't wreck the repl prompt ( #578 )
2023-09-22 12:17:45 -07:00
e9f6df7dca
use slices.DeleteFunc
2023-09-05 09:56:59 -07:00
42998d797d
subprocess llama.cpp server ( #401 )
...
* remove c code
* pack llama.cpp
* use request context for llama_cpp
* let llama_cpp decide the number of threads to use
* stop llama runner when app stops
* remove sample count and duration metrics
* use go generate to get libraries
* tmp dir for running llm
2023-08-30 16:35:03 -04:00
d791df75dd
check memory requirements before loading
2023-08-10 09:23:11 -07:00
a6f6d18f83
embed text document in modelfile
2023-08-08 11:27:17 -04:00
1c5a8770ee
read runner parameter options from map
...
- read runner options from map to see what was specified explicitly and overwrite zero values
2023-08-01 13:38:19 -04:00
daa0d1de7a
allow specifying zero values in modelfile
2023-08-01 13:37:50 -04:00
8609db77ea
use gin-contrib/cors middleware
2023-07-22 09:39:08 -07:00
e4d7f3e287
vendor in progress bar and change to bytes instead of bibytes ( #130 )
2023-07-19 17:24:03 -07:00
84200dcde6
use readline
2023-07-19 13:34:56 -07:00
5bea29f610
add new list command ( #97 )
2023-07-18 09:09:45 -07:00
28a136e9a3
modelfile params
2023-07-17 12:35:03 -07:00
a806b03f62
no errgroup
2023-07-11 14:58:10 -07:00
fd4792ec56
call llama.cpp directly from go
2023-07-11 11:59:18 -07:00
c4b9e84945
progress
2023-07-06 17:07:40 -07:00
3d6009aae3
run prompts
2023-07-06 17:07:40 -07:00
7cf5905063
display pull progress
2023-07-06 16:34:44 -04:00
68e6b4550c
use prompt templates
2023-07-06 16:34:44 -04:00
fd962a36e5
client updates
2023-07-06 16:34:44 -04:00
6093a88c1a
add llama.cpp go bindings
2023-07-06 16:34:44 -04:00
76cb60d496
wip go engine
...
Co-authored-by: Patrick Devine <pdevine@sonic.net >
2023-07-06 16:34:44 -04:00
