Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
cmd: preserve exact bytes when displaying template/system layers (#7586)
67691e4 Blake Mizerany committed 2 years ago
readme: add aichat terminal app to community integrations (#7418)
bebef1e Joey Zheng committed 2 years ago
readme: add GoLamify to community integrations (#7521)
36a8372 Prasad Bhalerao committed 2 years ago
readme: add browser extension that enables using Ollama for interacting with web pages (#5827)
4e94227 Ivo Stoykov committed 2 years ago
docs: update langchainpy.md with proper model name (#7527)
771fab1 Edward J. Schwartz committed 2 years ago
sched: Lift parallel restriction for multimodal models except mllama
6cd5668 Jesse Gross committed 2 years ago
One corrupt manifest should not wedge model operations (#7515)
a4c70fe Daniel Hiltgen committed 2 years ago
prompt: Use a single token when estimating mllama context size
34a7510 Jesse Gross committed 2 years ago