Ettore Di Giacinto
|
5cba71de70
|
Add stopwords, debug mode, and other API enhancements (#54)
Signed-off-by: mudler <mudler@mocaccino.org>
|
2 years ago |
|
Ettore Di Giacinto
|
4b7e83056d
|
Update .env
|
2 years ago |
|
Ettore Di Giacinto
|
ed954d66c3
|
Do not take all CPU by default (#50)
|
2 years ago |
|
Ettore Di Giacinto
|
f816dfae65
|
Add support for stablelm (#48)
Signed-off-by: mudler <mudler@mocaccino.org>
|
2 years ago |
|
Ettore Di Giacinto
|
142bcd66ca
|
Cleanup makefile, fix dep versions (#46)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
1c4fbaae20
|
Add support for cerebras (#45)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
d517a54e28
|
Major API enhancements (#44)
|
2 years ago |
Tyler Gillson
|
c905512bb0
|
Update example K8s manifests (#40)
|
2 years ago |
|
Ettore Di Giacinto
|
1254951fab
|
Add logo (#37)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
80f50e6ccd
|
Rename project to LocalAI (#35)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
7fec26f5d3
|
Enhancements (#34)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
a9a875ee2b
|
⬆️ Bump llama.cpp (#33)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
db5ac715f3
|
Use a reasonable default context size (#31)
|
2 years ago |
|
Ettore Di Giacinto
|
0b330d90ad
|
feat: drop embedded webui (#27)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
63601fabd1
|
feat: drop default model and llama-specific API (#26)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
1370b4482f
|
📖 Add prompt-templates examples (#25)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
Ettore Di Giacinto
|
b062f3142b
|
feat: enhance API, expose more parameters (#24)
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
Marc R Kellerman
|
c37175271f
|
feature: makefile & updates (#23)
Co-authored-by: mudler <mudler@c3os.io>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
|
2 years ago |
|
Ettore Di Giacinto
|
e8eab66c30
|
Merge pull request #22 from go-skynet/update-llama.cpp
⬆️ Update go-llama.cpp to `llama.cpp-2f7c8e0`
|
2 years ago |
mudler
|
a73a497143
|
Update llama.cpp
|
2 years ago |
|
Ettore Di Giacinto
|
6aea515e1d
|
Merge pull request #20 from go-skynet/mudler-patch-1
📖 Update README.md
|
2 years ago |
|
Ettore Di Giacinto
|
dfc2b7e02a
|
📖 Update README.md
|
2 years ago |
|
Ettore Di Giacinto
|
040290971c
|
Merge pull request #19 from go-skynet/tags
Use tags for go-llama.cpp
|
2 years ago |
|
mudler
|
553bad585e
|
Use tags for go-llama.cpp
|
2 years ago |
|
Ettore Di Giacinto
|
f76b612506
|
Merge pull request #17 from go-skynet/mudler-patch-1
Fix comment typo
|
2 years ago |
|
Ettore Di Giacinto
|
c4e94c88d7
|
Fix comment typo
Thanks to @deadprogram for noticing it!
|
2 years ago |
|
mudler
|
a9cd6b3ca3
|
ci: Fix tag detection for 'latest'
|
2 years ago |
|
mudler
|
e786576b95
|
Update README
|
2 years ago |
|
Ettore Di Giacinto
|
d426571789
|
Merge pull request #16 from go-skynet/fix_arm
Drop armv7 builds
|
2 years ago |
|
mudler
|
a896a2b5ad
|
Drop armv7 builds
|
2 years ago |
|
Ettore Di Giacinto
|
8273cd5c04
|
Merge pull request #15 from go-skynet/docker-compose
Add docker-compose file
|
2 years ago |
|
mudler
|
16f1281d38
|
Minor workflow fixes
|
2 years ago |
|
mudler
|
8042e9a2d6
|
Add docker-compose
Fixes #14
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
mudler
|
624092cb99
|
Update README
|
2 years ago |
|
mudler
|
a422a883ac
|
Minor rephrasing
|
2 years ago |
|
mudler
|
7858a97254
|
Update README
|
2 years ago |
|
mudler
|
5556aa46dd
|
Small refinements and refactors
|
2 years ago |
|
mudler
|
eb4257f946
|
Add .gitignore
|
2 years ago |
|
mudler
|
ae30bd346d
|
Reorganize repository layout
|
2 years ago |
|
mudler
|
93d8977ba2
|
Return model list
|
2 years ago |
|
mudler
|
f43aeeb4a1
|
Add both API endpoints (completion, chat)
|
2 years ago |
|
mudler
|
c17dcc5e9d
|
Allow to inject prompt as part of the call
|
2 years ago |
|
mudler
|
4a932483e1
|
Small fixup to template loading
|
2 years ago |
|
mudler
|
b710147b95
|
Add mutex on same models (parallel isn't supported yet)
|
2 years ago |
|
mudler
|
ba70363330
|
Use template input
|
2 years ago |
|
mudler
|
9fb581739b
|
Allow to template model prompts inputs
|
2 years ago |
|
mudler
|
48aca246e3
|
Drop unused interactive mode
|
2 years ago |
|
mudler
|
12eee097b7
|
Make it compatible with openAI api, support multiple models
Signed-off-by: mudler <mudler@c3os.io>
|
2 years ago |
|
mudler
|
b33d015b8c
|
Use go-llama.cpp
|
2 years ago |
|
Ettore Di Giacinto
|
b7c0a108f5
|
Update README.md
|
2 years ago |
