about the training data format of e2e training
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 25/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- machine-learning
Research direction
Start by locating the e2e training data preparation path and comparing its format with block-ep (PTQ) in the e2e (QAT) process. Check whether system, assistant, and think tokens are intentionally absent; done means documenting the behavior or defining the required format change.
Written by the indexing model from the issue text.
Description
I noticed that in the e2e training data preparing process, it seems that no special tokens like **"system", "assistant" or "think" tokens are included in the e2e data. So you are just using the same data format as block-ep(PTQ) in the e2e(QAT) process? No try for these structural information?
- Dominant language
- Python
- Stars
- 351
- Forks
- 38
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from OpenGVLab/EfficientQAT
-
Difficulty 1/5 Under an hour Newbie friendliness 78/100
OpenGVLab/EfficientQAT#31 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 28/100
OpenGVLab/EfficientQAT#34 ·
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
OpenGVLab/EfficientQAT#33 ·
-
About DatasetOpen
Difficulty 5/5 Over a week Newbie friendliness 20/100
OpenGVLab/EfficientQAT#30 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
OpenGVLab/EfficientQAT#29 · 4 comments ·
All issues in OpenGVLab/EfficientQAT
Similar issues
-
Difficulty 1/5 Under an hour Newbie friendliness 92/100
raullenchai/Rapid-MLX#4042 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
LearningCircuit/local-deep-research#7067 ·
Maintainers usually reply within 1 day
-
#bug
Difficulty 1/5 Under an hour Newbie friendliness 92/100
apache/superset#44923 · 1 comment ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
lawndoc/stack-back#123 ·