 royjhan
|
b7c622dd32
Merge branch 'main' into royh-batchembed
|
há 10 meses atrás |
 Roy Han
|
17de2b4405
Refactoring of legacy and new
|
há 10 meses atrás |
 Daniel Hiltgen
|
ccd7785859
Merge pull request #5243 from dhiltgen/modelfile_use_mmap
|
há 10 meses atrás |
|
royjhan
|
a5f23d766e
Merge branch 'main' into royh-batchembed
|
há 10 meses atrás |
|
royjhan
|
996bb1b85e
OpenAI: /v1/models and /v1/models/{model} compatibility (#5007)
|
há 10 meses atrás |
|
Roy Han
|
00a4cb26ca
use float32
|
há 10 meses atrás |
|
Roy Han
|
aee25acb5b
move normalization to go
|
há 10 meses atrás |
 Daniel Hiltgen
|
97c9e11768
Switch use_mmap to a pointer type
|
há 10 meses atrás |
|
Roy Han
|
80c1a3f812
playing around with truncate stuff
|
há 10 meses atrás |
|
Roy Han
|
5213c12354
clean up
|
há 10 meses atrás |
|
Roy Han
|
c406fa7a4c
api/embed draft
|
há 10 meses atrás |
|
Roy Han
|
ff191d7cba
Initial Draft
|
há 10 meses atrás |
|
Roy Han
|
0f87628b6d
Revert "Initial Batch Embedding"
|
há 10 meses atrás |
|
Daniel Hiltgen
|
7e7749224c
Fix use_mmap parsing for modelfiles
|
há 10 meses atrás |
|
royjhan
|
fedf71635e
Extend api/show and ollama show to return more model info (#4881)
|
há 10 meses atrás |
|
Roy Han
|
c22d54895a
Initial Batch Embedding
|
há 10 meses atrás |
|
Daniel Hiltgen
|
171796791f
Adjust mmap logic for cuda windows for faster model load
|
há 11 meses atrás |
|
royjhan
|
89c79bec8c
Add ModifiedAt Field to /api/show (#5033)
|
há 11 meses atrás |
 Patrick Devine
|
c69bc19e46
move OLLAMA_HOST to envconfig (#5009)
|
há 11 meses atrás |
|
royjhan
|
4bf1da4944
Separate ListResponse and ModelResponse for api/tags vs api/ps (#4842)
|
há 11 meses atrás |
 Michael Yang
|
c895a7d13f
some gocritic
|
há 11 meses atrás |
|
Patrick Devine
|
6845988807
Ollama `ps` command for showing currently loaded models (#4327)
|
há 1 ano atrás |
 Jeffrey Morgan
|
6602e793c0
Use `--quantize` flag and `quantize` api parameter (#4321)
|
há 1 ano atrás |
 Bruce MacDonald
|
c02db93243
omit empty done reason
|
há 1 ano atrás |
|
Bruce MacDonald
|
cfa84b8470
add done_reason to the api (#4235)
|
há 1 ano atrás |
|
Jeffrey Morgan
|
d5eec16d23
use model defaults for `num_gqa`, `rope_frequency_base ` and `rope_frequency_scale` (#1983)
|
há 1 ano atrás |
 Eli Bendersky
|
d77c1c5f9d
api: fill up API documentation (#3596)
|
há 1 ano atrás |
 Jackie Li
|
af47413dba
Add MarshalJSON to Duration (#3284)
|
há 1 ano atrás |
|
Patrick Devine
|
9009bedf13
better checking for OLLAMA_HOST variable (#3661)
|
há 1 ano atrás |
|
Jeffrey Morgan
|
993cf8bf55
llm: limit generation to 10x context size to avoid run on generations (#3918)
|
há 1 ano atrás |
