Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Make MTL refer to DeepPavlov 1.1 instead of my branch #366

Merged
merged 4 commits into from
Apr 4, 2023

Conversation

dimakarp1996
Copy link
Contributor

Make MTL refer to DeepPavlov 1.1 instead of my branch

@dimakarp1996 dimakarp1996 changed the base branch from main to dev March 27, 2023 14:54
@@ -1,6 +1,6 @@
FROM deeppavlov/base-gpu:0.17.5

RUN pip install git+https://github.com/deeppavlov/DeepPavlov.git@1f0bda76c7c3fd6ccd4a1c0c880c0fffb73522d1
RUN pip install git+https://github.com/deeppavlov/DeepPavlov.git@0448c732251ec171a85422eab197719f4e587334
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

для читабельности, предлагаю заменить хэш комита на тэг релиза (1.1.1)

@dilyararimovna dilyararimovna merged commit 8c0fdd8 into dev Apr 4, 2023
@dilyararimovna dilyararimovna deleted the mtl_dp_1.1 branch April 4, 2023 08:15
dilyararimovna pushed a commit that referenced this pull request Apr 6, 2023
* Update Dockerfile

* Update combined_classifier.json

* Update Dockerfile

* Update Dockerfile
dilyararimovna added a commit that referenced this pull request Apr 19, 2023
* feat: ru prompted dist based on llama

* feat: ru persona

* fix: versions

* fix duplicate endpoints, missing keys (#371)

* Make MTL refer to DeepPavlov 1.1 instead of my branch (#366)

* Update Dockerfile

* Update combined_classifier.json

* Update Dockerfile

* Update Dockerfile

* fix: starting openai services without dev.yml (#373)

* fix: reqs

* fix: dockerfile

* fix: pip update

* fix: reqs

* feat: using peft for gusev's model

* fix: reqs

* fix: working load

* feat: separate folder for peft transformers

* fix: revert to dev

* fix: transformers generation

* fix: use peft model

* fix: component yml

* fix: yml configs

* fix: no half precision

* fix: description

* fix: config is optional for some models

* fix: increase timeout

* fix: formatter

* fix: language

* fixed

* fix: rights

* fix: info ymls

* fix: 5sec timeout

* fix: 10sec timeout

* fix: gpu mem

* feat: ru pipeline and dockers

* feat: badlisted words ru

* feat: use fp16 for faster inference

* feat: rank sentences endpoint

* fix: endpoint func

* fix: ping pong

* fix: rannker url

* fix: prompt selector ru

* fix: env ru

* fix: sentence ranker

* fix: no-scripts selector

* fix: timeout 2.0 for ru toxic

* fix: first try for toxic model before ready

* fix: params for language

* fix: language

* fix: timoeout for dialogrpt

* fix: no use of toxic cls

* fix: revert timeout to 1sec

* feat: ru lang

* fix: ru persona

* feat: new prompt

* fix: prompt

* fix: prompt

* fix: prompt

* Update dream_persona.json

* Update dream_persona.json

* Update dream_persona_ru.json

* fix: rename distr

* fix: formatter

---------

Co-authored-by: Maxim Talimanchuk <[email protected]>
Co-authored-by: dimakarp1996 <[email protected]>
Co-authored-by: Fedor Ignatov <[email protected]>
Co-authored-by: Lidia Ostyakova <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants