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.

Sign up for GitHub

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

Jump to bottom

Some README and response_analysis cleanup #96

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Some README and response_analysis cleanup #96

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 2 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,9 +9,6 @@

We offer a suite of prompt decoders, albeit with a current focus on RankVicuna. Some of the code in this repository is borrowed from [RankGPT](https://github.com/sunnweiwei/RankGPT)!

# Releases
current_version = 0.2.6
Copy link
Member

Choose a reason for hiding this comment

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

Please add a section for the package installation and keep the version there
I use bumper to auto increase this every time I release a version

Copy link
Member Author

Choose a reason for hiding this comment

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

Why would this be needed though? Don't we automatically have this on top of README.md from PyPI? Not sure if I understand.

Copy link
Member

Choose a reason for hiding this comment

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

We do, but it is still nice to have this in the readme too, next to package installation or maybe under a release section to keep the log of release and features for each release or something like that.


## 📟 Instructions

### Create Conda Environment
Expand All @@ -33,8 +30,8 @@ pip install -r requirements.txt

### Run end to end Test
```bash
python src/rank_llm/scripts/run_rank_llm.py --model_path=castorini/rank_zephyr_7b_v1_full --top_k_candidates=100 --dataset=dl20 \
--retrieval_method=SPLADE++_EnsembleDistil_ONNX --prompt_mode=rank_GPT --context_size=4096 --variable_passages
python src/rank_llm/scripts/run_rank_llm.py --model_path=castorini/rank_zephyr_7b_v1_full --top_k_candidates=100 --dataset=dl19 \
--retrieval_method=SPLADE++_EnsembleDistil_ONNX --prompt_mode=rank_GPT --context_size=4096 --variable_passages
```

### Contributing
Expand Down
4 changes: 2 additions & 2 deletions src/rank_llm/scripts/run_response_analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,11 @@


def main(args):
response_analyzer = ResponseAnalyzer(args.files, 100, PromptMode.RANK_GPT)
response_analyzer = ResponseAnalyzer(args.files)
responses, num_passages = response_analyzer.read_saved_responses()
print("Normalized scores:")

print(response_analyzer.count_errors(responses, num_passages, args.verbose))
Copy link
Member

Choose a reason for hiding this comment

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

I added an boolean to count_errors for normalization, that is false by default, pleasee add an extra arg for that

print(response_analyzer.count_errors(verbose=args.verbose))
# Print normalized scores


Expand Down