Commit graph

882 commits

Author SHA1 Message Date
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
Michael Yang 865fceb73c chunked pipe 2023-08-28 18:34:53 -04:00
Michael Yang 72266c7684 bump chunk size to 95MB 2023-08-28 18:34:53 -04:00
Jeffrey Morgan d3b838ce60 update orca to orca-mini 2023-08-27 13:26:30 -04:00
Michael Yang e639a12fa1
Merge pull request #412 from jmorganca/mxyng/update-readme
update README.md
2023-08-26 21:26:34 -07:00
Michael Yang e82fcf30c6
Merge pull request #420 from jmorganca/mxyng/34b-mem-check
add 34b to mem check
2023-08-26 14:15:52 -07:00
Michael Yang 495e8b0a6a
Merge pull request #426 from jmorganca/default-template
set default template
2023-08-26 14:15:38 -07:00