Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,7 @@ tags:
|
|
11 |
- elite
|
12 |
- calcium
|
13 |
- qwen
|
|
|
14 |
model-index:
|
15 |
- name: Calcium-Opus-14B-Elite2
|
16 |
results:
|
@@ -28,7 +29,8 @@ model-index:
|
|
28 |
value: 61.76
|
29 |
name: averaged accuracy
|
30 |
source:
|
31 |
-
url:
|
|
|
32 |
name: Open LLM Leaderboard
|
33 |
- task:
|
34 |
type: text-generation
|
@@ -44,7 +46,8 @@ model-index:
|
|
44 |
value: 46.81
|
45 |
name: normalized accuracy
|
46 |
source:
|
47 |
-
url:
|
|
|
48 |
name: Open LLM Leaderboard
|
49 |
- task:
|
50 |
type: text-generation
|
@@ -60,7 +63,8 @@ model-index:
|
|
60 |
value: 36.1
|
61 |
name: exact match
|
62 |
source:
|
63 |
-
url:
|
|
|
64 |
name: Open LLM Leaderboard
|
65 |
- task:
|
66 |
type: text-generation
|
@@ -73,10 +77,11 @@ model-index:
|
|
73 |
num_few_shot: 0
|
74 |
metrics:
|
75 |
- type: acc_norm
|
76 |
-
value: 16
|
77 |
name: acc_norm
|
78 |
source:
|
79 |
-
url:
|
|
|
80 |
name: Open LLM Leaderboard
|
81 |
- task:
|
82 |
type: text-generation
|
@@ -91,7 +96,8 @@ model-index:
|
|
91 |
value: 22.24
|
92 |
name: acc_norm
|
93 |
source:
|
94 |
-
url:
|
|
|
95 |
name: Open LLM Leaderboard
|
96 |
- task:
|
97 |
type: text-generation
|
@@ -108,7 +114,8 @@ model-index:
|
|
108 |
value: 47.79
|
109 |
name: accuracy
|
110 |
source:
|
111 |
-
url:
|
|
|
112 |
name: Open LLM Leaderboard
|
113 |
---
|
114 |
|
@@ -229,5 +236,4 @@ Summarized results can be found [here](https://huggingface.co/datasets/open-llm-
|
|
229 |
|MATH Lvl 5 (4-Shot)| 46.90|
|
230 |
|GPQA (0-shot) | 16.00|
|
231 |
|MuSR (0-shot) | 22.24|
|
232 |
-
|MMLU-PRO (5-shot) | 47.79|
|
233 |
-
|
|
|
11 |
- elite
|
12 |
- calcium
|
13 |
- qwen
|
14 |
+
- trl
|
15 |
model-index:
|
16 |
- name: Calcium-Opus-14B-Elite2
|
17 |
results:
|
|
|
29 |
value: 61.76
|
30 |
name: averaged accuracy
|
31 |
source:
|
32 |
+
url: >-
|
33 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite2
|
34 |
name: Open LLM Leaderboard
|
35 |
- task:
|
36 |
type: text-generation
|
|
|
46 |
value: 46.81
|
47 |
name: normalized accuracy
|
48 |
source:
|
49 |
+
url: >-
|
50 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite2
|
51 |
name: Open LLM Leaderboard
|
52 |
- task:
|
53 |
type: text-generation
|
|
|
63 |
value: 36.1
|
64 |
name: exact match
|
65 |
source:
|
66 |
+
url: >-
|
67 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite2
|
68 |
name: Open LLM Leaderboard
|
69 |
- task:
|
70 |
type: text-generation
|
|
|
77 |
num_few_shot: 0
|
78 |
metrics:
|
79 |
- type: acc_norm
|
80 |
+
value: 16
|
81 |
name: acc_norm
|
82 |
source:
|
83 |
+
url: >-
|
84 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite2
|
85 |
name: Open LLM Leaderboard
|
86 |
- task:
|
87 |
type: text-generation
|
|
|
96 |
value: 22.24
|
97 |
name: acc_norm
|
98 |
source:
|
99 |
+
url: >-
|
100 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite2
|
101 |
name: Open LLM Leaderboard
|
102 |
- task:
|
103 |
type: text-generation
|
|
|
114 |
value: 47.79
|
115 |
name: accuracy
|
116 |
source:
|
117 |
+
url: >-
|
118 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite2
|
119 |
name: Open LLM Leaderboard
|
120 |
---
|
121 |
|
|
|
236 |
|MATH Lvl 5 (4-Shot)| 46.90|
|
237 |
|GPQA (0-shot) | 16.00|
|
238 |
|MuSR (0-shot) | 22.24|
|
239 |
+
|MMLU-PRO (5-shot) | 47.79|
|
|