current evals num_z=50
Browse files- data/code_eval_board.csv +2 -1
data/code_eval_board.csv
CHANGED
|
@@ -4,4 +4,5 @@ T,Models,ARC,HellaSwag,MMLU,TruthfulQA,Winogrande,GSM8K
|
|
| 4 |
🔶,Fredithefish/ReasonixPajama-3B-HF,0.15,0.24,0.21,0.94,0.01,0.44
|
| 5 |
🟢,mistralai/Mistral-7B-v0.1,0.54,0.51,0.46,0.75,0,0.91
|
| 6 |
🔶,rishiraj/meow,0.11,0.49,0.28,0.36,0.02,0.95
|
| 7 |
-
🔶,Q-bert/MetaMath-Cybertron-Starling,0.52,0.64,0.51,0.75,0.01,0.99
|
|
|
|
|
|
| 4 |
🔶,Fredithefish/ReasonixPajama-3B-HF,0.15,0.24,0.21,0.94,0.01,0.44
|
| 5 |
🟢,mistralai/Mistral-7B-v0.1,0.54,0.51,0.46,0.75,0,0.91
|
| 6 |
🔶,rishiraj/meow,0.11,0.49,0.28,0.36,0.02,0.95
|
| 7 |
+
🔶,Q-bert/MetaMath-Cybertron-Starling,0.52,0.64,0.51,0.75,0.01,0.99
|
| 8 |
+
🔶,upstage/SOLAR-10.7B-Instruct-v1.0,0.11,0.49,0.28,0.36,0.01,0.96
|