Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/jmorganca/ollama.git
. Pull mirroring updated
Sep 20, 2024
.
mxyng/head-kv
90f071c6
·
default head_kv to 1
·
Apr 02, 2024
subprocess
c672e465
·
Fix numgpu opt miscomparison
·
Apr 02, 2024
mxyng/fix-metal
80163ebc
·
fix metal gpu
·
Apr 02, 2024
modelfile-readme
83f6db36
·
Update docs/modelfile.md
·
Apr 01, 2024
pdevine/convert-redux
94ee63bb
·
make a common struct for models
·
Apr 01, 2024
mxyng/generate-output
1ec0df10
·
fix generate output
·
Apr 01, 2024
mxyng/decode-ggml-v2
d338d704
·
refactor model parsing
·
Apr 01, 2024
mxyng-patch-1
f31f2bed
·
Update troubleshooting link
·
Mar 28, 2024
mxyng/conditional-generate
5255d0af
·
fix: workflows
·
Mar 27, 2024
mxyng/origins
af8a8a6b
·
fix: trim quotes on OLLAMA_ORIGINS
·
Mar 27, 2024
gemma
7621fc4b
·
feed the linter
·
Mar 27, 2024
jmorganca/fix-windows-input
89a5ce3a
·
add some helpful comments
·
Mar 26, 2024
jmorganca/vendor-license
ae108fb7
·
add license in file header for vendored llama.cpp code
·
Mar 25, 2024
jmorganca/windows-build
cf2e13e6
·
remove need for `$VSINSTALLDIR` since build will fail if `ninja` cannot be found
·
Mar 25, 2024
fix-imports
517b4538
·
change `github.com/jmorganca/ollama` to `github.com/ollama/ollama`
·
Mar 25, 2024
brucemacd/community-docs
824a5d12
·
move community integrations to their own doc
·
Mar 25, 2024
bmizerany-patch-1
b00cf8b1
·
doc: specify ADAPTER is optional
·
Mar 24, 2024
guardlibs
be95d418
·
llm: prevent race appending to slice
·
Mar 23, 2024
dashq
8db8ff82
·
cmd: plumb quant through on show command
·
Mar 20, 2024
brucemacd/gpu-faq
f894bc3b
·
more specific AMD cards
·
Mar 20, 2024
Prev
1
…
17
18
19
20
21
22
23
24
25
…
43
Next