 Patrick Devine
|
6845988807
Ollama `ps` command for showing currently loaded models (#4327)
|
11 months ago |
 Jeffrey Morgan
|
6602e793c0
Use `--quantize` flag and `quantize` api parameter (#4321)
|
11 months ago |
 Bruce MacDonald
|
c02db93243
omit empty done reason
|
11 months ago |
|
Bruce MacDonald
|
cfa84b8470
add done_reason to the api (#4235)
|
11 months ago |
|
Jeffrey Morgan
|
d5eec16d23
use model defaults for `num_gqa`, `rope_frequency_base ` and `rope_frequency_scale` (#1983)
|
11 months ago |
 Eli Bendersky
|
d77c1c5f9d
api: fill up API documentation (#3596)
|
1 year ago |
 Jackie Li
|
af47413dba
Add MarshalJSON to Duration (#3284)
|
1 year ago |
|
Patrick Devine
|
9009bedf13
better checking for OLLAMA_HOST variable (#3661)
|
1 year ago |
|
Jeffrey Morgan
|
993cf8bf55
llm: limit generation to 10x context size to avoid run on generations (#3918)
|
1 year ago |
 Cheng
|
62be2050dd
chore: use errors.New to replace fmt.Errorf will much better (#3789)
|
1 year ago |
|
Eli Bendersky
|
ad90b9ab3d
api: start adding documentation to package api (#2878)
|
1 year ago |
 Michael Yang
|
01114b4526
fix: rope
|
1 year ago |
|
Michael Yang
|
9502e5661f
cgo quantize
|
1 year ago |
|
Michael Yang
|
be517e491c
no rope parameters
|
1 year ago |
|
Jeffrey Morgan
|
3b4bab3dc5
Fix embeddings load model behavior (#2848)
|
1 year ago |
 Ikko Eltociear Ashimine
|
e95b896790
Update types.go (#2744)
|
1 year ago |
 bnorick
|
caf2b13c10
Fix infinite keep_alive (#2480)
|
1 year ago |
|
Patrick Devine
|
b5cf31b460
add keep_alive to generate/chat/embedding api endpoints (#2146)
|
1 year ago |
|
Patrick Devine
|
7c40a67841
Save and load sessions (#2063)
|
1 year ago |
|
Michael Yang
|
745b5934fa
add model to ModelResponse
|
1 year ago |
|
Michael Yang
|
a38d88d828
api: add model for all requests
|
1 year ago |
 Patrick Devine
|
22e93efa41
add show info command and fix the modelfile
|
1 year ago |
|
Jeffrey Morgan
|
55978c1dc9
clean up cache api option
|
1 year ago |
|
Jeffrey Morgan
|
d4ebdadbe7
enable `cache_prompt` by default
|
1 year ago |
 K0IN
|
10da41d677
Add Cache flag to api (#1642)
|
1 year ago |
|
Bruce MacDonald
|
d99fa6ce0a
send empty messages on last chat response (#1530)
|
1 year ago |
|
Patrick Devine
|
d9e60f634b
add image support to the chat api (#1490)
|
1 year ago |
|
Patrick Devine
|
910e9401d0
Multimodal support (#1216)
|
1 year ago |
|
Jeffrey Morgan
|
9e1406e4ed
Don't expose model information in `/api/generate`
|
1 year ago |
|
Michael Yang
|
5d75505ebd
return model configuration in generate
|
1 year ago |
