Skip to content

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

Commits on main

Tidy up developer guide a little
Daniel Hiltgen committed 2 years ago
1b2d156
bump (#4597)
Michael Yang committed 2 years ago
714adb8
Merge pull request #4547 from dhiltgen/load_progress
Daniel Hiltgen committed 2 years ago
95b1133
Wire up load progress
Daniel Hiltgen committed 2 years ago
b37b496
d6f692a
Add isolated gpu test to troubleshooting
Daniel Hiltgen committed 2 years ago
f77713b
Use flash attention flag for now (#4580)
Jeffrey Morgan committed 2 years ago
38255d2
add phi 3 medium (#4578)
Michael committed 2 years ago
73630a7
chore: update tokenizer.go (#4571)
Ikko Eltociear Ashimine committed 2 years ago
955c317
add Ctrl + W shortcut
Josh Yan committed 2 years ago
353f83a
doc updates for the faq/troubleshooting (#4565)
Patrick Devine committed 2 years ago
3bade04
a6d0f44
Merge pull request #4268 from ollama/pdevine/llama3
Michael Yang committed 2 years ago
96236b7
Correct typo in error message (#4535)
Sang Park committed 2 years ago
4434d7f
simplify safetensors reading
Michael Yang committed 2 years ago
171eb04
add test
Michael Yang committed 2 years ago
3591bbe
fix conversion for f16 or f32 inputs
Michael Yang committed 2 years ago
34d5ef2
cleanup
Michael Yang committed 2 years ago
bbbd9f2
bpe pretokenizer
Michael Yang committed 2 years ago
547132e
add missing file
Patrick Devine committed 2 years ago
2d315ba
add fixes for llama
Patrick Devine committed 2 years ago
d355d20
llama3 conversion
Patrick Devine committed 2 years ago
c8cf0d9
add safetensors version
Patrick Devine committed 2 years ago
4730762
some changes for llama3
Patrick Devine committed 2 years ago
d88582d
2f81b3d
set llama.cpp submodule commit to `614d3b9`
jmorganca committed 2 years ago
5cab137
updated updateURL
Josh Yan committed 2 years ago
8aadad9
fix quantize file types
Michael Yang committed 2 years ago
807d092
tidy intermediate blobs
Michael Yang committed 2 years ago
f36f1d6