add eval results
Browse files
README.md
CHANGED
@@ -19,8 +19,108 @@ tags:
|
|
19 |
datasets:
|
20 |
- jondurbin/truthy-dpo-v0.1
|
21 |
model-index:
|
22 |
-
|
23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
base_model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
25 |
license: apache-2.0
|
26 |
language:
|
|
|
19 |
datasets:
|
20 |
- jondurbin/truthy-dpo-v0.1
|
21 |
model-index:
|
22 |
+
- name: WestLake-7B-v2-laser-truthy-dpo
|
23 |
+
results:
|
24 |
+
- task:
|
25 |
+
type: text-generation
|
26 |
+
name: Text Generation
|
27 |
+
dataset:
|
28 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
29 |
+
type: ai2_arc
|
30 |
+
config: ARC-Challenge
|
31 |
+
split: test
|
32 |
+
args:
|
33 |
+
num_few_shot: 25
|
34 |
+
metrics:
|
35 |
+
- type: acc_norm
|
36 |
+
value: 73.89
|
37 |
+
name: normalized accuracy
|
38 |
+
source:
|
39 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
40 |
+
name: Open LLM Leaderboard
|
41 |
+
- task:
|
42 |
+
type: text-generation
|
43 |
+
name: Text Generation
|
44 |
+
dataset:
|
45 |
+
name: HellaSwag (10-Shot)
|
46 |
+
type: hellaswag
|
47 |
+
split: validation
|
48 |
+
args:
|
49 |
+
num_few_shot: 10
|
50 |
+
metrics:
|
51 |
+
- type: acc_norm
|
52 |
+
value: 88.85
|
53 |
+
name: normalized accuracy
|
54 |
+
source:
|
55 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
56 |
+
name: Open LLM Leaderboard
|
57 |
+
- task:
|
58 |
+
type: text-generation
|
59 |
+
name: Text Generation
|
60 |
+
dataset:
|
61 |
+
name: MMLU (5-Shot)
|
62 |
+
type: cais/mmlu
|
63 |
+
config: all
|
64 |
+
split: test
|
65 |
+
args:
|
66 |
+
num_few_shot: 5
|
67 |
+
metrics:
|
68 |
+
- type: acc
|
69 |
+
value: 64.84
|
70 |
+
name: accuracy
|
71 |
+
source:
|
72 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
73 |
+
name: Open LLM Leaderboard
|
74 |
+
- task:
|
75 |
+
type: text-generation
|
76 |
+
name: Text Generation
|
77 |
+
dataset:
|
78 |
+
name: TruthfulQA (0-shot)
|
79 |
+
type: truthful_qa
|
80 |
+
config: multiple_choice
|
81 |
+
split: validation
|
82 |
+
args:
|
83 |
+
num_few_shot: 0
|
84 |
+
metrics:
|
85 |
+
- type: mc2
|
86 |
+
value: 69.81
|
87 |
+
source:
|
88 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
89 |
+
name: Open LLM Leaderboard
|
90 |
+
- task:
|
91 |
+
type: text-generation
|
92 |
+
name: Text Generation
|
93 |
+
dataset:
|
94 |
+
name: Winogrande (5-shot)
|
95 |
+
type: winogrande
|
96 |
+
config: winogrande_xl
|
97 |
+
split: validation
|
98 |
+
args:
|
99 |
+
num_few_shot: 5
|
100 |
+
metrics:
|
101 |
+
- type: acc
|
102 |
+
value: 86.66
|
103 |
+
name: accuracy
|
104 |
+
source:
|
105 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
106 |
+
name: Open LLM Leaderboard
|
107 |
+
- task:
|
108 |
+
type: text-generation
|
109 |
+
name: Text Generation
|
110 |
+
dataset:
|
111 |
+
name: GSM8k (5-shot)
|
112 |
+
type: gsm8k
|
113 |
+
config: main
|
114 |
+
split: test
|
115 |
+
args:
|
116 |
+
num_few_shot: 5
|
117 |
+
metrics:
|
118 |
+
- type: acc
|
119 |
+
value: 68.16
|
120 |
+
name: accuracy
|
121 |
+
source:
|
122 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
123 |
+
name: Open LLM Leaderboard
|
124 |
base_model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
125 |
license: apache-2.0
|
126 |
language:
|