[example] add qa recipe #37
Merged
Conversation
This file contains hidden or 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
robin1001
reviewed
Sep 2, 2025
robin1001
reviewed
Sep 10, 2025
west/dataset/dataset.py
Outdated
| try: | ||
| x['txt'] = x['txt'].decode('utf8') | ||
| x['wav'] = io.BytesIO(x['wav']) | ||
| if "messages" in x.keys(): |
Collaborator
There was a problem hiding this comment.
这块我们不加了，
对于 SFT 的数据，我们系统上设计只支持 jsonl 的
| if 'messages' in item: # OpenAI role-content based SFT data | ||
| # OpenAI role-content based SFT data | ||
| # At least one pair of "user" and "assistant" | ||
| if 'messages' in item and len(item["messages"]) >= 2: |
Collaborator
There was a problem hiding this comment.
这个直接在下面 assert len(item['messages']) >= 2
| @@ -0,0 +1,82 @@ | |||
| #!/usr/bin/env python3 | |||
Collaborator
There was a problem hiding this comment.
文件命名上我们都是用下划线形式compute_acc_of_contain.py
examples/belle_1.4M_qa/run.sh
Outdated
| python west/bin/decode.py \ | ||
| --data_path $data/chinese_qa.jsonl \ | ||
| --model_dir $mdir \ | ||
| --result_path $mdir/result.txt |
robin1001
approved these changes
Sep 10, 2025
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Outdated suggestions cannot be applied.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.
Uh oh!
There was an error while loading. Please reload this page.