Skip to content

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

Commits on main

x: add experimental agent loop (#13628)
Parth Sareen committed 10 months ago
76912c0
olmo3: fix flaky test (#13629)
Devon Rifkin committed 10 months ago
6c3faaf
e51dead
d087e46
docs: fix broken .md links and render issues (#13550)
Vallabh Mahajan committed 11 months ago
18fdcc9
amd: use GTT on iGPUs on linux (#13196)
Daniel Hiltgen committed 11 months ago
7ad0369
172b592
add REQUIRES command to Modelfile (#13361)
Jeffrey Morgan committed 11 months ago
8852220
parsers/renderers: functiongemma (#13521)
Parth Sareen committed 11 months ago
7325791
GGML update to ec98e2002 (#13451)
Daniel Hiltgen committed 11 months ago
49a9c9b
1c09403
DeepseekV3 Family Parser (#13484)
Grace committed 11 months ago
a013693
revert granite-embedding (#13505)
Michael Yang committed 11 months ago
f6a016f
types: ConfigV2 and RootFS (#13504)
Bruce MacDonald committed 11 months ago
45c4739
remove unnecessary code (#13502)
Michael Yang committed 11 months ago
2dd029d
use ollama engine for bert models (#13501)
Michael Yang committed 11 months ago
903b1fc
89eb795
llama/parsers/renderers: nemotron 3 nano (#13489)
Parth Sareen committed 11 months ago
7e3ea81
fix: qwen2.5 vl rope (#13486)
Michael Yang committed 11 months ago
971d625
model: add olmo3 and olmo3.1 (#13415)
Parth Sareen committed 11 months ago
ffbe8e0
DeepseekV3 family renderer (#13180)
Grace committed 11 months ago
2c63943
renderers: add olmo3.1 and olmo3 fixes (#13447)
Parth Sareen committed 11 months ago
e3731fb