 Daniel Hiltgen
|
7e7749224c
Fix use_mmap parsing for modelfiles
|
hai 10 meses |
 royjhan
|
fedf71635e
Extend api/show and ollama show to return more model info (#4881)
|
hai 10 meses |
|
Daniel Hiltgen
|
171796791f
Adjust mmap logic for cuda windows for faster model load
|
hai 10 meses |
|
royjhan
|
89c79bec8c
Add ModifiedAt Field to /api/show (#5033)
|
hai 10 meses |
 Patrick Devine
|
c69bc19e46
move OLLAMA_HOST to envconfig (#5009)
|
hai 10 meses |
|
royjhan
|
4bf1da4944
Separate ListResponse and ModelResponse for api/tags vs api/ps (#4842)
|
hai 11 meses |
 Michael Yang
|
c895a7d13f
some gocritic
|
hai 11 meses |
|
Patrick Devine
|
6845988807
Ollama `ps` command for showing currently loaded models (#4327)
|
hai 11 meses |
 Jeffrey Morgan
|
6602e793c0
Use `--quantize` flag and `quantize` api parameter (#4321)
|
hai 11 meses |
 Bruce MacDonald
|
c02db93243
omit empty done reason
|
hai 11 meses |
|
Bruce MacDonald
|
cfa84b8470
add done_reason to the api (#4235)
|
hai 11 meses |
|
Jeffrey Morgan
|
d5eec16d23
use model defaults for `num_gqa`, `rope_frequency_base ` and `rope_frequency_scale` (#1983)
|
hai 11 meses |
 Eli Bendersky
|
d77c1c5f9d
api: fill up API documentation (#3596)
|
hai 1 ano |
 Jackie Li
|
af47413dba
Add MarshalJSON to Duration (#3284)
|
hai 1 ano |
|
Patrick Devine
|
9009bedf13
better checking for OLLAMA_HOST variable (#3661)
|
hai 1 ano |
|
Jeffrey Morgan
|
993cf8bf55
llm: limit generation to 10x context size to avoid run on generations (#3918)
|
hai 1 ano |
 Cheng
|
62be2050dd
chore: use errors.New to replace fmt.Errorf will much better (#3789)
|
hai 1 ano |
|
Eli Bendersky
|
ad90b9ab3d
api: start adding documentation to package api (#2878)
|
hai 1 ano |
|
Michael Yang
|
01114b4526
fix: rope
|
hai 1 ano |
|
Michael Yang
|
9502e5661f
cgo quantize
|
hai 1 ano |
|
Michael Yang
|
be517e491c
no rope parameters
|
hai 1 ano |
|
Jeffrey Morgan
|
3b4bab3dc5
Fix embeddings load model behavior (#2848)
|
hai 1 ano |
 Ikko Eltociear Ashimine
|
e95b896790
Update types.go (#2744)
|
hai 1 ano |
 bnorick
|
caf2b13c10
Fix infinite keep_alive (#2480)
|
hai 1 ano |
|
Patrick Devine
|
b5cf31b460
add keep_alive to generate/chat/embedding api endpoints (#2146)
|
hai 1 ano |
|
Patrick Devine
|
7c40a67841
Save and load sessions (#2063)
|
hai 1 ano |
|
Michael Yang
|
745b5934fa
add model to ModelResponse
|
hai 1 ano |
|
Michael Yang
|
a38d88d828
api: add model for all requests
|
hai 1 ano |
 Patrick Devine
|
22e93efa41
add show info command and fix the modelfile
|
hai 1 ano |
|
Jeffrey Morgan
|
55978c1dc9
clean up cache api option
|
hai 1 ano |
