update readme

README.md

@@ -14,21 +14,20 @@ license: apache-2.0
 
 To run this code locally:
 
-1. Change the environment variables in `src/env` and `src/about`.
+1. Change the environment variables in `src/env` to add your API keys.
 
-2. Run the following command to start the server locally:
+2. To run the backend server + UI locally, run the following command:
 ```
-./start.sh RUN_MODE="LOCAL" LOCAL_MODEL_NAME="<any huggingface model you want to try>"
+./start.sh RUN_MODE="LOCAL" LOCAL_MODEL_NAME="<any huggingface or openai model you want to try>"
 
 Eg:
 ./start.sh RUN_MODE="LOCAL" LOCAL_MODEL_NAME="hf-internal-testing/tiny-random-gpt2"
 ```
-This does not upload/download any requests/results files.
-
 
 ### Adhoc evaluation:
 
-To generate result files adhoc to directly upload to results, run the following command after modifying `adhoc.py` to your needs:
+To run only the backend server locally to quickly get the evaluation results, run the following command:
 ```
-./run-adhoc.sh
+./run-adhoc.sh LOCAL_MODEL_NAME="<any huggingface or openai model you want to try>"
 ```
+This will still allow you to save your benchmarking results in the folder `output-data`.

src/about.py

@@ -175,7 +175,7 @@ f"How would you score the model's answer compared to the gold answer (using the
 ## Reproducibility
 1. Clone this repo by following the steps provided [here.](https://huggingface.co/spaces/lamini/leaderboard?clone=true)
 
-2. Now change the environment variables in `src/env` to add your api keys.
+2. Now change the environment variables in `src/env` to add your API keys.
 
 There are 2 ways to run this code locally: