Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
pipeline_tag: text-generation
|
| 3 |
inference: false
|
| 4 |
-
license:
|
| 5 |
library_name: transformers
|
| 6 |
model-index:
|
| 7 |
- name: ibm/PowerMoE-3b
|
|
@@ -9,8 +9,8 @@ model-index:
|
|
| 9 |
- task:
|
| 10 |
type: text-generation
|
| 11 |
dataset:
|
| 12 |
-
|
| 13 |
-
|
| 14 |
metrics:
|
| 15 |
- name: accuracy-norm
|
| 16 |
type: accuracy-norm
|
|
@@ -19,8 +19,8 @@ model-index:
|
|
| 19 |
- task:
|
| 20 |
type: text-generation
|
| 21 |
dataset:
|
| 22 |
-
|
| 23 |
-
|
| 24 |
metrics:
|
| 25 |
- name: accuracy
|
| 26 |
type: accuracy
|
|
@@ -29,8 +29,8 @@ model-index:
|
|
| 29 |
- task:
|
| 30 |
type: text-generation
|
| 31 |
dataset:
|
| 32 |
-
|
| 33 |
-
|
| 34 |
metrics:
|
| 35 |
- name: accuracy-norm
|
| 36 |
type: accuracy-norm
|
|
@@ -39,8 +39,8 @@ model-index:
|
|
| 39 |
- task:
|
| 40 |
type: text-generation
|
| 41 |
dataset:
|
| 42 |
-
|
| 43 |
-
|
| 44 |
metrics:
|
| 45 |
- name: accuracy-norm
|
| 46 |
type: accuracy-norm
|
|
@@ -49,8 +49,8 @@ model-index:
|
|
| 49 |
- task:
|
| 50 |
type: text-generation
|
| 51 |
dataset:
|
| 52 |
-
|
| 53 |
-
|
| 54 |
metrics:
|
| 55 |
- name: accuracy-norm
|
| 56 |
type: accuracy-norm
|
|
@@ -59,8 +59,8 @@ model-index:
|
|
| 59 |
- task:
|
| 60 |
type: text-generation
|
| 61 |
dataset:
|
| 62 |
-
|
| 63 |
-
|
| 64 |
metrics:
|
| 65 |
- name: accuracy-norm
|
| 66 |
type: accuracy-norm
|
|
@@ -69,8 +69,8 @@ model-index:
|
|
| 69 |
- task:
|
| 70 |
type: text-generation
|
| 71 |
dataset:
|
| 72 |
-
|
| 73 |
-
|
| 74 |
metrics:
|
| 75 |
- name: accuracy
|
| 76 |
type: accuracy
|
|
@@ -79,8 +79,8 @@ model-index:
|
|
| 79 |
- task:
|
| 80 |
type: text-generation
|
| 81 |
dataset:
|
| 82 |
-
|
| 83 |
-
|
| 84 |
metrics:
|
| 85 |
- name: accuracy
|
| 86 |
type: accuracy
|
|
@@ -89,8 +89,8 @@ model-index:
|
|
| 89 |
- task:
|
| 90 |
type: text-generation
|
| 91 |
dataset:
|
| 92 |
-
|
| 93 |
-
|
| 94 |
metrics:
|
| 95 |
- name: accuracy
|
| 96 |
type: accuracy
|
|
@@ -99,8 +99,8 @@ model-index:
|
|
| 99 |
- task:
|
| 100 |
type: text-generation
|
| 101 |
dataset:
|
| 102 |
-
|
| 103 |
-
|
| 104 |
metrics:
|
| 105 |
- name: pass@1
|
| 106 |
type: pass@1
|
|
@@ -109,8 +109,8 @@ model-index:
|
|
| 109 |
- task:
|
| 110 |
type: text-generation
|
| 111 |
dataset:
|
| 112 |
-
|
| 113 |
-
|
| 114 |
metrics:
|
| 115 |
- name: pass@1
|
| 116 |
type: pass@1
|
|
@@ -152,4 +152,4 @@ output = tokenizer.batch_decode(output)
|
|
| 152 |
# loop over the batch to print, in this example the batch size is 1
|
| 153 |
for i in output:
|
| 154 |
print(i)
|
| 155 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
pipeline_tag: text-generation
|
| 3 |
inference: false
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
library_name: transformers
|
| 6 |
model-index:
|
| 7 |
- name: ibm/PowerMoE-3b
|
|
|
|
| 9 |
- task:
|
| 10 |
type: text-generation
|
| 11 |
dataset:
|
| 12 |
+
type: lm-eval-harness
|
| 13 |
+
name: ARC
|
| 14 |
metrics:
|
| 15 |
- name: accuracy-norm
|
| 16 |
type: accuracy-norm
|
|
|
|
| 19 |
- task:
|
| 20 |
type: text-generation
|
| 21 |
dataset:
|
| 22 |
+
type: lm-eval-harness
|
| 23 |
+
name: BoolQ
|
| 24 |
metrics:
|
| 25 |
- name: accuracy
|
| 26 |
type: accuracy
|
|
|
|
| 29 |
- task:
|
| 30 |
type: text-generation
|
| 31 |
dataset:
|
| 32 |
+
type: lm-eval-harness
|
| 33 |
+
name: Hellaswag
|
| 34 |
metrics:
|
| 35 |
- name: accuracy-norm
|
| 36 |
type: accuracy-norm
|
|
|
|
| 39 |
- task:
|
| 40 |
type: text-generation
|
| 41 |
dataset:
|
| 42 |
+
type: lm-eval-harness
|
| 43 |
+
name: OpenBookQA
|
| 44 |
metrics:
|
| 45 |
- name: accuracy-norm
|
| 46 |
type: accuracy-norm
|
|
|
|
| 49 |
- task:
|
| 50 |
type: text-generation
|
| 51 |
dataset:
|
| 52 |
+
type: lm-eval-harness
|
| 53 |
+
name: PIQA
|
| 54 |
metrics:
|
| 55 |
- name: accuracy-norm
|
| 56 |
type: accuracy-norm
|
|
|
|
| 59 |
- task:
|
| 60 |
type: text-generation
|
| 61 |
dataset:
|
| 62 |
+
type: lm-eval-harness
|
| 63 |
+
name: Winogrande
|
| 64 |
metrics:
|
| 65 |
- name: accuracy-norm
|
| 66 |
type: accuracy-norm
|
|
|
|
| 69 |
- task:
|
| 70 |
type: text-generation
|
| 71 |
dataset:
|
| 72 |
+
type: lm-eval-harness
|
| 73 |
+
name: MMLU
|
| 74 |
metrics:
|
| 75 |
- name: accuracy
|
| 76 |
type: accuracy
|
|
|
|
| 79 |
- task:
|
| 80 |
type: text-generation
|
| 81 |
dataset:
|
| 82 |
+
type: lm-eval-harness
|
| 83 |
+
name: GSM8k (5 shot)
|
| 84 |
metrics:
|
| 85 |
- name: accuracy
|
| 86 |
type: accuracy
|
|
|
|
| 89 |
- task:
|
| 90 |
type: text-generation
|
| 91 |
dataset:
|
| 92 |
+
type: lm-eval-harness
|
| 93 |
+
name: math (4 shot)
|
| 94 |
metrics:
|
| 95 |
- name: accuracy
|
| 96 |
type: accuracy
|
|
|
|
| 99 |
- task:
|
| 100 |
type: text-generation
|
| 101 |
dataset:
|
| 102 |
+
type: bigcode-eval
|
| 103 |
+
name: humaneval
|
| 104 |
metrics:
|
| 105 |
- name: pass@1
|
| 106 |
type: pass@1
|
|
|
|
| 109 |
- task:
|
| 110 |
type: text-generation
|
| 111 |
dataset:
|
| 112 |
+
type: bigcode-eval
|
| 113 |
+
name: MBPP
|
| 114 |
metrics:
|
| 115 |
- name: pass@1
|
| 116 |
type: pass@1
|
|
|
|
| 152 |
# loop over the batch to print, in this example the batch size is 1
|
| 153 |
for i in output:
|
| 154 |
print(i)
|
| 155 |
+
```
|