baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
3288 commits 1 branch 0 tags 13 MiB
Commit graph

3288 commits

This branch
This branch
All branches
Author SHA1 Message Date
Jeffrey Morgan
61dda6a5e0 set minimum CMAKE_OSX_DEPLOYMENT_TARGET to 11.0 2023-09-06 19:56:50 -04:00
Michael Yang
e1f9ced568
Merge pull request #479 from jmorganca/mxyng/dockerfile 
update dockerfile
 2023-09-06 15:44:24 -07:00
Michael Yang
9795b43d93 update dockerfile 2023-09-06 15:31:25 -07:00
Michael Yang
0980d5c7e3
Merge pull request #478 from jmorganca/mxyng/cleanup 
remove unused openssh key types
 2023-09-06 15:18:54 -07:00
Michael Yang
0dae34b6a7 remove unused openssh key types 2023-09-06 14:34:09 -07:00
Michael Yang
83c6be1666
fix model manifests (#477) 2023-09-06 17:30:08 -04:00
Patrick Devine
1adfa67589
tighten up the error string for ollama show flags (#476) 2023-09-06 13:38:49 -07:00
Patrick Devine
790d24eb7b
add show command (#474) 2023-09-06 11:04:17 -07:00
Jeffrey Morgan
7de300856b use osPath in gpu check 2023-09-05 21:52:21 -04:00
Jeffrey Morgan
213ffdb548 macos amd64 compatibility fixes 2023-09-05 21:33:31 -04:00
Michael Yang
d42d88386a
Merge pull request #473 from jmorganca/mxyng/fix-manifest-path 
create manifests directory
 2023-09-05 17:37:41 -07:00
Ackermann Yuriy
154f24af91
Added missing options params to the embeddings docs (#472) 2023-09-05 20:18:49 -04:00
Michael Yang
a1ecdd36d5 create manifests directory 2023-09-05 17:10:40 -07:00
Bruce MacDonald
d18282bfda
metal: add missing barriers for mul-mat (#469) 2023-09-05 19:37:13 -04:00
Michael Yang
9ae76ba8c9
Merge pull request #471 from jmorganca/mxyng/fix-empty-response 
fix empty response
 2023-09-05 15:23:05 -07:00
Michael Yang
2bc06565c7 fix empty response 2023-09-05 15:03:24 -07:00
Michael Yang
d1c2558f7e
Merge pull request #461 from jmorganca/mxyng/fix-inherit-params 
fix inherit params
 2023-09-05 12:30:23 -07:00
Michael Yang
7b5aefb427
Merge pull request #462 from jmorganca/mxyng/rm-marshal-prompt 
remove marshalPrompt which is no longer needed
 2023-09-05 11:48:41 -07:00
Michael Yang
06ef90c051 fix parameter inheritence 
parameters are not inherited because they are processed differently from
other layer. fix this by explicitly merging the inherited params into
the new params. parameter values defined in the new modelfile will
override those defined in the inherited modelfile. array lists are
replaced instead of appended
 2023-09-05 11:40:20 -07:00
Michael Yang
7efbc84320
Merge pull request #464 from jmorganca/mxyng/fix-num-keep 
fix num_keep
 2023-09-05 11:30:45 -07:00
Michael Yang
e9f6df7dca use slices.DeleteFunc 2023-09-05 09:56:59 -07:00
Jeffrey Morgan
7fa6e51686
generate binary dependencies based on GOARCH on macos (#459) 2023-09-05 12:53:57 -04:00
Michael Yang
8dc68417e7
Merge pull request #463 from jmorganca/mxyng/fix-last-token 
fix not forwarding last token
 2023-09-05 09:01:32 -07:00
Michael Yang
681f3c4c42 fix num_keep 2023-09-03 17:47:49 -04:00
Michael Yang
59a705525c fix not forwarding last token 2023-09-03 17:46:50 -04:00
Michael Yang
5d3f314b0b remove marshalPrompt which is no longer needed 2023-09-03 17:01:05 -04:00
Michael Yang
adaa13088b
Merge pull request #457 from sqs/dont-html-escape-prompt 
do not HTML-escape prompt
 2023-09-01 17:41:53 -07:00
Quinn Slack
62d29b2157 do not HTML-escape prompt 
The `html/template` package automatically HTML-escapes interpolated strings in templates. This behavior is undesirable because it causes prompts like `<h1>hello` to be escaped to `&lt;h1&gt;hello` before being passed to the LLM.

The included test case passes, but before the code change, it failed:

```
--- FAIL: TestModelPrompt
    images_test.go:21: got "a&lt;h1&gt;b", want "a<h1>b"
```
 2023-09-01 17:16:38 -05:00
Michael Yang
ed19d10aa5
update readme (#451) 
* update readme

* readme: more run examples
 2023-09-01 16:44:14 -04:00
Michael Yang
36c2f45c40
Merge pull request #450 from jmorganca/mxyng/update-readme 
update readme
 2023-09-01 08:21:49 -07:00
Michael Yang
742226625f update readme 2023-09-01 10:54:31 -04:00
Matt Williams
6bb8a16ccb
Merge pull request #273 from jmorganca/matt/moreexamples 
Create a sentiments example
 2023-08-31 16:31:59 -07:00
Jeffrey Morgan
a5dbcf2e73 app: dont package ggml-metal.metal 2023-08-31 17:41:09 -04:00
Michael Yang
9304f0e7a8
Merge pull request #443 from jmorganca/mxyng/fix-list-models 
windows: fix filepath bugs
 2023-08-31 14:19:10 -07:00
Michael Yang
6578b2f8a1
Merge pull request #448 from callmephilip/patch-1 
fix spelling errors in example prompts
 2023-08-31 08:57:07 -07:00
Michael Yang
1c8fd627ad windows: fix create modelfile 2023-08-31 09:47:10 -04:00
Michael Yang
ae950b00f1 windows: fix delete 2023-08-31 09:47:10 -04:00
Michael Yang
eeb40a672c fix list models for windows 2023-08-31 09:47:10 -04:00
Michael Yang
0f541a0367 s/ListResponseModel/ModelResponse/ 2023-08-31 09:47:10 -04:00
Philip Nuzhnyi
1363f537ce
fix spelling errors in prompt 2023-08-31 10:02:46 +01:00
Jeffrey Morgan
bc3e21fdc6 update README.md 2023-08-30 17:56:14 -04:00
Jeffrey Morgan
a82eb275ff update docs for subprocess 2023-08-30 17:54:02 -04:00
Bruce MacDonald
f964aea9a2 remove test not applicate to subprocess 2023-08-30 16:36:11 -04:00
Bruce MacDonald
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
Quinn Slack
f4432e1dba
treat stop as stop sequences, not exact tokens (#442) 
The `stop` option to the generate API is a list of sequences that should cause generation to stop. Although these are commonly called "stop tokens", they do not necessarily correspond to LLM tokens (per the LLM's tokenizer). For example, if the caller sends a generate request with `"stop":["\n"]`, then generation should stop on any token containing `\n` (and trim `\n` from the output), not just if the token exactly matches `\n`. If `stop` were interpreted strictly as LLM tokens, then it would require callers of the generate API to know the LLM's tokenizer and enumerate many tokens in the `stop` list.

Fixes https://github.com/jmorganca/ollama/issues/295.
 2023-08-30 11:53:42 -04:00
Michael Yang
982c535428
Merge pull request #428 from jmorganca/mxyng/upload-chunks 
update upload chunks
 2023-08-30 07:47:17 -07:00
Michael Yang
7df342a6ea
Merge pull request #421 from jmorganca/mxyng/f16-metal 
allow F16 to use metal
 2023-08-29 06:32:59 -07:00
Patrick Devine
8bbff2df98
add model IDs (#439) 2023-08-28 20:50:24 -07:00
Michael Yang
16b06699fd remove unused parameter 2023-08-28 18:35:18 -04:00
Michael Yang
246dc65417 loosen http status code checks 2023-08-28 18:34:53 -04:00