Update app.py
Browse files
app.py
CHANGED
|
@@ -134,6 +134,9 @@ Your final output should consist of only one of the following:
|
|
| 134 |
|
| 135 |
Do not include any explanation, reasoning, or additional text in your output."""}
|
| 136 |
|
|
|
|
|
|
|
|
|
|
| 137 |
def add_new_eval(
|
| 138 |
model: str,
|
| 139 |
model_family: str,
|
|
@@ -208,6 +211,8 @@ def add_new_eval(
|
|
| 208 |
num_questions = 0
|
| 209 |
task_ids = []
|
| 210 |
|
|
|
|
|
|
|
| 211 |
with open(f"scored/{organisation}_{model}.jsonl", "w") as scored_file: # check where is this saved
|
| 212 |
with open(file_path, 'r') as f:
|
| 213 |
data = json.load(f)
|
|
@@ -307,7 +312,7 @@ def add_new_eval(
|
|
| 307 |
"system_prompt": system_prompt,
|
| 308 |
"url": url,
|
| 309 |
"organisation": organisation,
|
| 310 |
-
"score": score #s / ref_scores_len,#[val_or_test],
|
| 311 |
"date": datetime.datetime.today().strftime('%Y-%m-%d')
|
| 312 |
}
|
| 313 |
|
|
|
|
| 134 |
|
| 135 |
Do not include any explanation, reasoning, or additional text in your output."""}
|
| 136 |
|
| 137 |
+
def call_start():
|
| 138 |
+
return format_log("We are starting your evaluation. This can take a few minutes.")
|
| 139 |
+
|
| 140 |
def add_new_eval(
|
| 141 |
model: str,
|
| 142 |
model_family: str,
|
|
|
|
| 211 |
num_questions = 0
|
| 212 |
task_ids = []
|
| 213 |
|
| 214 |
+
call_start()
|
| 215 |
+
|
| 216 |
with open(f"scored/{organisation}_{model}.jsonl", "w") as scored_file: # check where is this saved
|
| 217 |
with open(file_path, 'r') as f:
|
| 218 |
data = json.load(f)
|
|
|
|
| 312 |
"system_prompt": system_prompt,
|
| 313 |
"url": url,
|
| 314 |
"organisation": organisation,
|
| 315 |
+
"score": score, #s / ref_scores_len,#[val_or_test],
|
| 316 |
"date": datetime.datetime.today().strftime('%Y-%m-%d')
|
| 317 |
}
|
| 318 |
|