Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
sample: add numerical stability to temperature/softmax transform (#9631)
7e34f4f Parth Sareen committed 1 year ago
sample: temporarily use grammars for constrained generation in new engine (#9586)
e093db9 Jeffrey Morgan committed 1 year ago
model: Update encoder cache to use multimodal input processing handler
a1cda80 Jesse Gross committed 1 year ago
ollamarunner: Don't panic for unimplemented features at runtime.
4614faf Jesse Gross committed 1 year ago