Commit
•
d632a1c
1
Parent(s):
fc2a2de
Adding Evaluation Results (#8)
Browse files- Adding Evaluation Results (cdea28de8eab555e22a96bc8fef329d6b2f2c8f4)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
@@ -1,8 +1,111 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
language:
|
4 |
- pt
|
5 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
---
|
7 |
The Cabrita model is a collection of continued pre-trained and tokenizer-adapted models for the Portuguese language.
|
8 |
This artifact is the 3 billion size variant.
|
@@ -19,4 +122,17 @@ open_llama_3b option.
|
|
19 |
archivePrefix={arXiv},
|
20 |
primaryClass={cs.CL}
|
21 |
}
|
22 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- pt
|
4 |
- en
|
5 |
+
license: apache-2.0
|
6 |
+
model-index:
|
7 |
+
- name: open-cabrita3b
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
type: text-generation
|
11 |
+
name: Text Generation
|
12 |
+
dataset:
|
13 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
14 |
+
type: ai2_arc
|
15 |
+
config: ARC-Challenge
|
16 |
+
split: test
|
17 |
+
args:
|
18 |
+
num_few_shot: 25
|
19 |
+
metrics:
|
20 |
+
- type: acc_norm
|
21 |
+
value: 33.79
|
22 |
+
name: normalized accuracy
|
23 |
+
source:
|
24 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
|
25 |
+
name: Open LLM Leaderboard
|
26 |
+
- task:
|
27 |
+
type: text-generation
|
28 |
+
name: Text Generation
|
29 |
+
dataset:
|
30 |
+
name: HellaSwag (10-Shot)
|
31 |
+
type: hellaswag
|
32 |
+
split: validation
|
33 |
+
args:
|
34 |
+
num_few_shot: 10
|
35 |
+
metrics:
|
36 |
+
- type: acc_norm
|
37 |
+
value: 55.35
|
38 |
+
name: normalized accuracy
|
39 |
+
source:
|
40 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
|
41 |
+
name: Open LLM Leaderboard
|
42 |
+
- task:
|
43 |
+
type: text-generation
|
44 |
+
name: Text Generation
|
45 |
+
dataset:
|
46 |
+
name: MMLU (5-Shot)
|
47 |
+
type: cais/mmlu
|
48 |
+
config: all
|
49 |
+
split: test
|
50 |
+
args:
|
51 |
+
num_few_shot: 5
|
52 |
+
metrics:
|
53 |
+
- type: acc
|
54 |
+
value: 25.16
|
55 |
+
name: accuracy
|
56 |
+
source:
|
57 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
|
58 |
+
name: Open LLM Leaderboard
|
59 |
+
- task:
|
60 |
+
type: text-generation
|
61 |
+
name: Text Generation
|
62 |
+
dataset:
|
63 |
+
name: TruthfulQA (0-shot)
|
64 |
+
type: truthful_qa
|
65 |
+
config: multiple_choice
|
66 |
+
split: validation
|
67 |
+
args:
|
68 |
+
num_few_shot: 0
|
69 |
+
metrics:
|
70 |
+
- type: mc2
|
71 |
+
value: 38.5
|
72 |
+
source:
|
73 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
|
74 |
+
name: Open LLM Leaderboard
|
75 |
+
- task:
|
76 |
+
type: text-generation
|
77 |
+
name: Text Generation
|
78 |
+
dataset:
|
79 |
+
name: Winogrande (5-shot)
|
80 |
+
type: winogrande
|
81 |
+
config: winogrande_xl
|
82 |
+
split: validation
|
83 |
+
args:
|
84 |
+
num_few_shot: 5
|
85 |
+
metrics:
|
86 |
+
- type: acc
|
87 |
+
value: 59.43
|
88 |
+
name: accuracy
|
89 |
+
source:
|
90 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
|
91 |
+
name: Open LLM Leaderboard
|
92 |
+
- task:
|
93 |
+
type: text-generation
|
94 |
+
name: Text Generation
|
95 |
+
dataset:
|
96 |
+
name: GSM8k (5-shot)
|
97 |
+
type: gsm8k
|
98 |
+
config: main
|
99 |
+
split: test
|
100 |
+
args:
|
101 |
+
num_few_shot: 5
|
102 |
+
metrics:
|
103 |
+
- type: acc
|
104 |
+
value: 0.99
|
105 |
+
name: accuracy
|
106 |
+
source:
|
107 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
|
108 |
+
name: Open LLM Leaderboard
|
109 |
---
|
110 |
The Cabrita model is a collection of continued pre-trained and tokenizer-adapted models for the Portuguese language.
|
111 |
This artifact is the 3 billion size variant.
|
|
|
122 |
archivePrefix={arXiv},
|
123 |
primaryClass={cs.CL}
|
124 |
}
|
125 |
+
```
|
126 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
127 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_22h__open-cabrita3b)
|
128 |
+
|
129 |
+
| Metric |Value|
|
130 |
+
|---------------------------------|----:|
|
131 |
+
|Avg. |35.54|
|
132 |
+
|AI2 Reasoning Challenge (25-Shot)|33.79|
|
133 |
+
|HellaSwag (10-Shot) |55.35|
|
134 |
+
|MMLU (5-Shot) |25.16|
|
135 |
+
|TruthfulQA (0-shot) |38.50|
|
136 |
+
|Winogrande (5-shot) |59.43|
|
137 |
+
|GSM8k (5-shot) | 0.99|
|
138 |
+
|