Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
model: treat 'user defined' tokens as special tokens (#11077)
9e125d8 Jeffrey Morgan committed 1 year ago
readme: add ollama-launcher to community integrations (#11080)
5020289 NGC13009 committed 1 year ago
tools: loosen tool parsing to allow for more formats (#11030)
9f8a18e Jeffrey Morgan committed 1 year ago
readme: add ollama-multirun to community integrations (#11038)
deaabe2 Attogram Project committed 1 year ago
docs: update link to AMD drivers in linux.md (#10973)
fc03096 Krzysztof Jeziorny committed 1 year ago
Revert "server: add model capabilities to the list endpoint (#10174)" (#11004)
09d308d Jeffrey Morgan committed 1 year ago
Merge pull request #10987 from ollama/drifkin/export-thinking-parser
2cf007c Devon Rifkin committed 1 year ago
server: add model capabilities to the list endpoint (#10174)
0943001 JasonHonKL committed 1 year ago
readme: add SimpleOllamaUnity to community integrations (#10817)
5c42800 HardCodeDev committed 1 year ago
tools: resiliency upgrade to name and arg extraction from template (#10917)
65f10c2 Parth Sareen committed 1 year ago
kvcache: Skip computing causal mask for worst case graph reservation
ea79003 Jesse Gross committed 1 year ago