Update README.md
Browse files
README.md
CHANGED
@@ -48,15 +48,4 @@ The model is capable of quality code, math, and logical reasoning. Try whatever
|
|
48 |
|
49 |
# Evaluations
|
50 |
|
51 |
-
|
52 |
-
|----------|-------|------|-----:|--------|-----:|---|-----:|
|
53 |
-
|arc_easy |Yaml |none | 0|acc |0.8552|± |0.0072|
|
54 |
-
| | |none | 0|acc_norm|0.8237|± |0.0078|
|
55 |
-
|boolq |Yaml |none | 0|acc |0.8749|± |0.0058|
|
56 |
-
|hellaswag |Yaml |none | 0|acc |0.6734|± |0.0047|
|
57 |
-
| | |none | 0|acc_norm|0.8489|± |0.0036|
|
58 |
-
|openbookqa|Yaml |none | 0|acc |0.3640|± |0.0215|
|
59 |
-
| | |none | 0|acc_norm|0.4780|± |0.0224|
|
60 |
-
|piqa |Yaml |none | 0|acc |0.8330|± |0.0087|
|
61 |
-
| | |none | 0|acc_norm|0.8368|± |0.0086|
|
62 |
-
|winogrande|Yaml |none | 0|acc |0.7703|± |0.0118|
|
|
|
48 |
|
49 |
# Evaluations
|
50 |
|
51 |
+
TODO
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|