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

updated spaces for numbered steps in the evaluation portion of the readme #2

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

updated spaces for numbered steps in the evaluation portion of the readme #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9b2f30a
updated spaces for numbered steps in the evaluation portion of the re…
ckgresla Oct 2, 2023
d371b79
ran an eval with zephyr-7b-beta from HF, included results
ckgresla Nov 28, 2023
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
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ python inference.py --model-path {model_path} --model-id {model_id} --question-f

We provide the inference results of various LLMs on `model_output/outputs` directory. Note that for the inference of FLASK-Hard, you can simply replace the `--question-file` argument to `../evaluation_set/flask_hard_evaluation.jsonl`.

### Step3. Model Evaluation
### Step 3. Model Evaluation
After inference, we can evaluate the model using FLASK evaluation protocol. Run the following command for evaluation.

```
Expand All @@ -54,7 +54,7 @@ python gpt4_eval.py -q {output_error_file} -a {answer_file} -o {output_review_fi

We provide the GPT-4 evaluation result of various models in `gpt_review/outputs` directory.

### Step4. Aggregation and Analysis
### Step 4. Aggregation and Analysis
After evaluation, FLASK enables fine-grained analysis depending on the skills, domains, and the difficulty levels.

For analyzing the performance for each `skill`, run the following command:
Expand Down
Loading