Adding evaluation on scenario-specific quantifiable metrics #76
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Co-authored-by: RulinShao <srl0310@outlook.com>
… for chatting (#1827)
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
…el worker. (#1866)
* Add sotopia data with the format * add template (#2) * support together ai ft --------- Co-authored-by: Ruiyi Wang <ruiyi.pamela.wang@gmail.com>
* Add multiturn data and processing file * Split train/test based on difficulty
Co-authored-by: Ruiyi Wang <ruiyi.pamela.wang@gmail.com>
* move file * add requirements.txt * add setup and test dir * add pre-commit-config * fix install dependencies issues * fix install dependencies issues * fix nonexisting pytest * fix mypy.yml * fix mypy.yml --------- Co-authored-by: Ruiyi Wang <ruiyi.pamela.wang@gmail.com>
* close together ai issue * add together ai inference example --------- Co-authored-by: Ruiyi Wang <ruiyi.pamela.wang@gmail.com>
* support qlora * upload dummy conversation data * delete doc and docker * update pyproject pip install package * continue cleaning * delete more files * delete a format
* support qlora * upload dummy conversation data * delete doc and docker * update pyproject pip install package * continue cleaning * delete more files * delete a format * add llm_deploy * add testing scripts * update deployment readme * update readme and fix some bug * finalize the inference and deployment based on vllm
* add writing and exp template * fix typo in issue template
* Add multiturn data and processing file * Split train/test based on difficulty * move multiturn data folder under together-ai-ft/
* support qlora mistral training * added deep speed to requirements * add mistral ft code * add deepspeed file and add inferene template * add deepspeed file and add inferene template * delete deepspeed, already included in the pyproject * Update .gitignore --------- Co-authored-by: Jasonqi146 <jasonqi146@gmail.com> Co-authored-by: ruiyiw <ruiyi.pamela.wang@gmail.com>
* support qlora mistral training * added deep speed to requirements * temporary save for switching disk region * added shuffle and access token * finished training pipeline; need to fix inference * finished training pipeline; need to fix inference * fixed inference pipeline * commiting to test deepspeed * added featurere to remove seq longer than 2048 * try to merge * minor changes * minor changes --------- Co-authored-by: lwaekfjlk <1125027232@qq.com> Co-authored-by: zqi2cmu <zqi2@andrew.cmu.edu>
Jasonqi146
force-pushed
the
feature/hard-scenario-eval
branch
from
5312e95 to
0e8d939
Compare
|
@Jasonqi146 can you create a folder named similar to scenario-specific evaluation? So that we have two types of eval: scenario-independent ones (sotopia) and sceario-dependent ones (your quantitiave analysis) |
lwaekfjlk
pushed a commit
that referenced
this pull request
Nov 17, 2023
lwaekfjlk
pushed a commit
that referenced
this pull request
Mar 14, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Closes #29
📑 Description
Generate scenario-specific prompts and use OpenAI API to determine quantifiable losses/gains for hard scenarios
✅ Checks
type/descript(e.g.feature/add-llm-agents)ℹ Additional Information