Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

Added headless-ollama (#4612)
Nischal Jain committed 2 years ago
85169e8
llm: always add bos token to prompt (#4941)
Jeffrey Morgan committed 2 years ago
34f1427
46a7f1e
fix parsing big endian gguf
Michael Yang committed 2 years ago
620d5c5
update import.md
Michael Yang committed 2 years ago
b9ce7bf
Merge pull request #4909 from dhiltgen/oneapi_disable
Daniel Hiltgen committed 2 years ago
cddc633
fix create model when template detection errors
Michael Yang committed 2 years ago
030e765
Add ability to skip oneapi generate
Daniel Hiltgen committed 2 years ago
ab8c929
llm: patch to fix qwen 2 temporarily on nvidia (#4897)
Jeffrey Morgan committed 2 years ago
ce0dc33
detect chat template from KV
Michael Yang committed 2 years ago
9b6c2e6
API app/browser access (#4879)
royjhan committed 2 years ago
1a29e9a
de5beb0
docs(tools): add gollama (#4829)
Sam committed 2 years ago
98e6592
proper utf16 support
Michael Yang committed 2 years ago
66ab487
22fcf8f
API PS Documentation (#4822)
royjhan committed 2 years ago
28c7813
1d8616d
update create handler to use model.Name
Michael Yang committed 2 years ago
d61ef8b
Merge pull request #4570 from ollama/mxyng/slices
Michael Yang committed 2 years ago
89d9900
local wording was confusing people
Michael committed 2 years ago
4a04871
gofmt, goimports
Michael Yang committed 2 years ago
6297f85
warn on intrange, usestdlibvars
Michael Yang committed 2 years ago
ed56428
disable intrange
Michael Yang committed 2 years ago
ad40b92
more lint
Michael Yang committed 2 years ago
8ce4032
no usestdlibvars
Michael Yang committed 2 years ago
4266046
lint windows
Michael Yang committed 2 years ago
e919f68
lint linux
Michael Yang committed 2 years ago
bf7edb0