Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

d3450dd
109d4fc
thinking: fix double emit when no opening tag
Devon Rifkin committed 1 year ago
2cb0a58
7cce5aa
gpt-oss: convert from hugging face format (#11907)
Michael Yang committed 1 year ago
4ae4f47
llm: Don't always evict models in CPU-only mode
Jesse Gross committed 1 year ago
073fa31
openai: remove reasoning as an api.Options (#11993)
Michael Yang committed 1 year ago
91fc3c4
Merge pull request #11973 from ollama/drifkin/bpe
Devon Rifkin committed 1 year ago
6de6266
model: add bpe roundtripping tests
Devon Rifkin committed 1 year ago
463a6ca
model: fix boundary in bpe
Devon Rifkin committed 1 year ago
fc5fb09
05ccb17
disable output_all (#11959)
Michael Yang committed 1 year ago
f804e8a
readme: add Andes to community integrations (#11952)
Ruslan Suleymanov committed 1 year ago
470d580
llm: Check for nil memory data before printing
Jesse Gross committed 1 year ago
e3ade45
048bd44
ec8bf5e
abeec24
gpt-oss: disable quantized kv cache (#11929)
Michael Yang committed 1 year ago
df335aa
handle cgo flags in docker build (#11909)
Daniel Hiltgen committed 1 year ago
5271ff8
d6f7233