Jeffrey Morgan
|
527cc97899
llama: update vendored code to commit 40c6d79f (#7875)
|
hai 4 meses |
Parth Sareen
|
c6c526275d
api: add generate endpoint for structured outputs (#7939)
|
hai 4 meses |
Parth Sareen
|
630e7dc6ff
api: structured outputs - chat endpoint (#7900)
|
hai 4 meses |
Parth Sareen
|
5f8051180e
Enable index tracking for tools - openai api support (#7888)
|
hai 5 meses |
Evan
|
d48c1c5a44
api: fix typos in Go Doc comments (#7620)
|
hai 5 meses |
Jesse Gross
|
a909417602
runner.go: Remove unused arguments
|
hai 6 meses |
Michael Yang
|
8e6da3cbc5
update deprecated warnings
|
hai 8 meses |
Chua Chee Seng
|
d4a7216c82
Fixed invalid option provided not displaying the invalid option name problem. (#6202)
|
hai 8 meses |
Daniel Hiltgen
|
f457d63400
Implement linux NUMA detection
|
hai 9 meses |
royjhan
|
1b44d873e7
Add Metrics to `api\embed` response (#5709)
|
hai 9 meses |
Jeffrey Morgan
|
46e6327e0f
api: add stringifier for `Tool` (#5891)
|
hai 9 meses |
Tibor Schmidt
|
f3d7a481b7
feat: add support for min_p (resolve #1142) (#1825)
|
hai 9 meses |
Jeffrey Morgan
|
84e5721f3a
always provide content even if empty (#5778)
|
hai 9 meses |
Michael Yang
|
b255445557
marshal json automatically for some template values (#5758)
|
hai 9 meses |
Michael Yang
|
c279f96371
remove ToolCall from GenerateResponse
|
hai 9 meses |
Michael Yang
|
499e87c9ba
Merge pull request #5730 from ollama/mxyng/cleanup
|
hai 9 meses |
Michael Yang
|
d290e87513
add suffix support to generate endpoint
|
hai 10 meses |
Michael Yang
|
5a83f79afd
remove unneeded tool calls
|
hai 9 meses |
Michael Yang
|
64039df6d7
Merge pull request #5284 from ollama/mxyng/tools
|
hai 9 meses |
Jeffrey Morgan
|
7ac6d462ec
server: return empty slice on empty `/api/embed` request (#5713)
|
hai 9 meses |
Michael Yang
|
d02bbebb11
tools
|
hai 10 meses |
Jeffrey Morgan
|
9e35d9bbee
server: lowercase roles for compatibility with clients (#5695)
|
hai 9 meses |
royjhan
|
b9f5e16c80
Introduce `/api/embed` endpoint supporting batch embedding (#5127)
|
hai 9 meses |
Patrick Devine
|
057d31861e
remove template (#5655)
|
hai 9 meses |
Daniel Hiltgen
|
ccd7785859
Merge pull request #5243 from dhiltgen/modelfile_use_mmap
|
hai 10 meses |
royjhan
|
996bb1b85e
OpenAI: /v1/models and /v1/models/{model} compatibility (#5007)
|
hai 10 meses |
Daniel Hiltgen
|
97c9e11768
Switch use_mmap to a pointer type
|
hai 10 meses |
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 |