feature(wqj): add vllm_test.py in ding/worker #853
+539
−1
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
wqj2004
changed the title
wqj2004
changed the title
PaParaZz1
changed the title
PaParaZz1
requested changes
Jan 19, 2025
ding/worker/vllm_test_wqj.py
Outdated
|
|
||
| model=HuggingFaceModelGenerator('/mnt/afs/share/Qwen2-VL-7B',temperature=0.5) #设置一个temperature就好了,可以做到生成多个候选答案 | ||
|
|
||
| def get_prompts_qwen(questions: list,modality: str): |
ding/worker/vllm_test_wqj.py
Outdated
| stop_token_ids = None | ||
| return prompts,stop_token_ids | ||
|
|
||
| def get_multi_modal_input(modality,filenames,questions): |
ding/worker/vllm_test_wqj.py
Outdated
| #img_names=['/mnt/afs/niuyazhe/data/meme/data/Eimages/Eimages/Eimages/image_ (2)'] | ||
| num_prompts=len(questions) | ||
| image_repeat_prob=None | ||
| modality = 'image' |
There was a problem hiding this comment.
use enum class to control this field rather than the naive string
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Outdated suggestions cannot be applied.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.
Overview
The whole RLHF training pipeline
Goal
In this PR, we need to finish the
collectorpart in the above figure and add its unittest.TODO