Commit graph

9 commits

Author SHA1 Message Date
Co Tran
79b1c5415f
[Kan-103] add support toxic/jailbreak model (#49)
* add toxic/jailbreak model

* fix path loading model

* fix syntax

* fix bug,lint, format

* fix bug

* formatting

* add parallel + chunking

* fix bug

* working version

* fix onnnx name erorr

* device

* fix jailbreak config

* fix syntax error

* format

* add requirement + cli download for dockerfile

* add task

* add skeleton change for envoy filter for prompt guard

* fix hardware config

* fix bug

* add config changes

* add gitignore

* merge main

* integrate arch-guard with filter

* add hardware config

* nothing

* add hardware config feature

* fix requirement

* fix chat ui

* fix onnx

* fix lint

* remove non intel cpu

* remove onnx

* working version

* modify docker

* fix guard time

* add nvidia support

* remove nvidia

* add gpu

* add gpu

* add gpu support

* add gpu support for compose

* add gpu support for compose

* add gpu support for compose

* add gpu support for compose

* add gpu support for compose

* fix docker file

* fix int test

* correct gpu docker

* upgrad python 10

* fix logits to be gpu compatible

* default to cpu dockerfile

* resolve comments

* fix lint + unused parameters

* fix

* remove eetq install for cpu

* remove deploy gpu

---------

Co-authored-by: Adil Hafeez <adil@katanemo.com>
2024-09-23 12:07:31 -07:00
Adil Hafeez
97b47c2ab4
Include param default in parameters (#68)
* Include param default in parameters

* improve default param pr

* fix integration tests
2024-09-20 09:02:24 -07:00
Adil Hafeez
4438dc7979
remove embeddings config from config (#64)
* remove embeddings config from config

* remove embedding provider
2024-09-19 17:49:42 -07:00
Adil Hafeez
2cd5ec5adf
use openai standard response in arch-fc and in gradio client (#62)
* use openai standard response in arch-fc and in gradio client

also fix code bug in usage

* fix int test
2024-09-19 12:19:14 -07:00
Adil Hafeez
3135ba8eae
add ability to override default values from config (#58) 2024-09-17 22:37:58 -07:00
José Ulises Niño Rivera
9f3c845610
Add ability to stream a response (#50)
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-09-17 16:12:41 -07:00
Adil Hafeez
8a265de7c6
Propagate enums from prompt-target to bolt-fc (#56) 2024-09-17 12:03:21 -07:00
Adil Hafeez
63143fbd01
add bolt guard config (#55) 2024-09-17 10:59:50 -07:00
Adil Hafeez
060a0d665e
improve service names (#54)
- embedding-server => model_server
- public-types => public_types
- chatbot-ui => chatbot_ui
- function-calling => function_calling
2024-09-17 08:47:35 -07:00