Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
readme: rename community integration from Claude Dev to Cline (#10168)
19c0c25 qwerty108109 committed 1 year ago
types: allow tool function parameters with a single type or an array of types (#9434)
2f723ac Alex Rozgo committed 1 year ago
Merge pull request #10169 from ollama/drifkin/fix-contributing-formatting
249fbbe Devon Rifkin committed 1 year ago
ml/backend/ggml: create a new file descriptor for tensor (#10133)
0f3f9e3 Daniel Hipke committed 1 year ago
model: fix issues with spm tokenizer for Gemma 3 (#10081)
b51e0f3 Jeffrey Morgan committed 1 year ago
kvcache: Add check for values that fall out of sliding window cache
b429700 jmorganca committed 1 year ago
chore(all): replace instances of interface with any (#10067)
9876c9f Bruce MacDonald committed 1 year ago
api: return model capabilities from the show endpoint (#10066)
e172f09 Bruce MacDonald committed 1 year ago
server/internal/client/ollama: cache completed chunks (#9933)
ef27d52 Blake Mizerany committed 1 year ago
runner: Release semaphore and improve error messages on failures
b2a4652 Jesse Gross committed 1 year ago
readme: add Writeopia to community integrations (#10042)
071a987 Leandro Borges Ferreira committed 1 year ago