 Michael Yang
|
499e87c9ba
Merge pull request #5730 from ollama/mxyng/cleanup
|
10 mesi fa |
|
Michael Yang
|
d290e87513
add suffix support to generate endpoint
|
11 mesi fa |
|
Michael Yang
|
5a83f79afd
remove unneeded tool calls
|
10 mesi fa |
|
Michael Yang
|
64039df6d7
Merge pull request #5284 from ollama/mxyng/tools
|
10 mesi fa |
 Jeffrey Morgan
|
7ac6d462ec
server: return empty slice on empty `/api/embed` request (#5713)
|
10 mesi fa |
|
Michael Yang
|
d02bbebb11
tools
|
11 mesi fa |
|
Jeffrey Morgan
|
9e35d9bbee
server: lowercase roles for compatibility with clients (#5695)
|
10 mesi fa |
 royjhan
|
b9f5e16c80
Introduce `/api/embed` endpoint supporting batch embedding (#5127)
|
10 mesi fa |
 Patrick Devine
|
057d31861e
remove template (#5655)
|
10 mesi fa |
 Daniel Hiltgen
|
ccd7785859
Merge pull request #5243 from dhiltgen/modelfile_use_mmap
|
10 mesi fa |
|
royjhan
|
996bb1b85e
OpenAI: /v1/models and /v1/models/{model} compatibility (#5007)
|
10 mesi fa |
 Daniel Hiltgen
|
97c9e11768
Switch use_mmap to a pointer type
|
10 mesi fa |
|
Daniel Hiltgen
|
7e7749224c
Fix use_mmap parsing for modelfiles
|
10 mesi fa |
|
royjhan
|
fedf71635e
Extend api/show and ollama show to return more model info (#4881)
|
11 mesi fa |
|
Daniel Hiltgen
|
171796791f
Adjust mmap logic for cuda windows for faster model load
|
11 mesi fa |
|
royjhan
|
89c79bec8c
Add ModifiedAt Field to /api/show (#5033)
|
11 mesi fa |
|
Patrick Devine
|
c69bc19e46
move OLLAMA_HOST to envconfig (#5009)
|
11 mesi fa |
|
royjhan
|
4bf1da4944
Separate ListResponse and ModelResponse for api/tags vs api/ps (#4842)
|
11 mesi fa |
|
Michael Yang
|
c895a7d13f
some gocritic
|
1 anno fa |
|
Patrick Devine
|
6845988807
Ollama `ps` command for showing currently loaded models (#4327)
|
1 anno fa |
|
Jeffrey Morgan
|
6602e793c0
Use `--quantize` flag and `quantize` api parameter (#4321)
|
1 anno fa |
 Bruce MacDonald
|
c02db93243
omit empty done reason
|
1 anno fa |
|
Bruce MacDonald
|
cfa84b8470
add done_reason to the api (#4235)
|
1 anno fa |
|
Jeffrey Morgan
|
d5eec16d23
use model defaults for `num_gqa`, `rope_frequency_base ` and `rope_frequency_scale` (#1983)
|
1 anno fa |
 Eli Bendersky
|
d77c1c5f9d
api: fill up API documentation (#3596)
|
1 anno fa |
 Jackie Li
|
af47413dba
Add MarshalJSON to Duration (#3284)
|
1 anno fa |
|
Patrick Devine
|
9009bedf13
better checking for OLLAMA_HOST variable (#3661)
|
1 anno fa |
|
Jeffrey Morgan
|
993cf8bf55
llm: limit generation to 10x context size to avoid run on generations (#3918)
|
1 anno fa |
 Cheng
|
62be2050dd
chore: use errors.New to replace fmt.Errorf will much better (#3789)
|
1 anno fa |
|
Eli Bendersky
|
ad90b9ab3d
api: start adding documentation to package api (#2878)
|
1 anno fa |
