Update README.md
Browse files
README.md
CHANGED
@@ -30,7 +30,8 @@ model-index:
|
|
30 |
value: 79.23
|
31 |
name: strict accuracy
|
32 |
source:
|
33 |
-
url:
|
|
|
34 |
name: Open LLM Leaderboard
|
35 |
- task:
|
36 |
type: text-generation
|
@@ -45,7 +46,8 @@ model-index:
|
|
45 |
value: 50.57
|
46 |
name: normalized accuracy
|
47 |
source:
|
48 |
-
url:
|
|
|
49 |
name: Open LLM Leaderboard
|
50 |
- task:
|
51 |
type: text-generation
|
@@ -60,7 +62,8 @@ model-index:
|
|
60 |
value: 34.21
|
61 |
name: exact match
|
62 |
source:
|
63 |
-
url:
|
|
|
64 |
name: Open LLM Leaderboard
|
65 |
- task:
|
66 |
type: text-generation
|
@@ -72,10 +75,11 @@ model-index:
|
|
72 |
num_few_shot: 0
|
73 |
metrics:
|
74 |
- type: acc_norm
|
75 |
-
value: 17
|
76 |
name: acc_norm
|
77 |
source:
|
78 |
-
url:
|
|
|
79 |
name: Open LLM Leaderboard
|
80 |
- task:
|
81 |
type: text-generation
|
@@ -90,7 +94,8 @@ model-index:
|
|
90 |
value: 14.56
|
91 |
name: acc_norm
|
92 |
source:
|
93 |
-
url:
|
|
|
94 |
name: Open LLM Leaderboard
|
95 |
- task:
|
96 |
type: text-generation
|
@@ -107,8 +112,10 @@ model-index:
|
|
107 |
value: 47.69
|
108 |
name: accuracy
|
109 |
source:
|
110 |
-
url:
|
|
|
111 |
name: Open LLM Leaderboard
|
|
|
112 |
---
|
113 |
# tempesthenno--nuslerp (BASE MODEL)
|
114 |
|
@@ -241,5 +248,4 @@ slices:
|
|
241 |
|MATH Lvl 5 (4-Shot)|47.36|
|
242 |
|GPQA (0-shot) |17.00|
|
243 |
|MuSR (0-shot) |14.56|
|
244 |
-
|MMLU-PRO (5-shot) |47.69|
|
245 |
-
|
|
|
30 |
value: 79.23
|
31 |
name: strict accuracy
|
32 |
source:
|
33 |
+
url: >-
|
34 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
|
35 |
name: Open LLM Leaderboard
|
36 |
- task:
|
37 |
type: text-generation
|
|
|
46 |
value: 50.57
|
47 |
name: normalized accuracy
|
48 |
source:
|
49 |
+
url: >-
|
50 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
|
51 |
name: Open LLM Leaderboard
|
52 |
- task:
|
53 |
type: text-generation
|
|
|
62 |
value: 34.21
|
63 |
name: exact match
|
64 |
source:
|
65 |
+
url: >-
|
66 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
|
67 |
name: Open LLM Leaderboard
|
68 |
- task:
|
69 |
type: text-generation
|
|
|
75 |
num_few_shot: 0
|
76 |
metrics:
|
77 |
- type: acc_norm
|
78 |
+
value: 17
|
79 |
name: acc_norm
|
80 |
source:
|
81 |
+
url: >-
|
82 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
|
83 |
name: Open LLM Leaderboard
|
84 |
- task:
|
85 |
type: text-generation
|
|
|
94 |
value: 14.56
|
95 |
name: acc_norm
|
96 |
source:
|
97 |
+
url: >-
|
98 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
|
99 |
name: Open LLM Leaderboard
|
100 |
- task:
|
101 |
type: text-generation
|
|
|
112 |
value: 47.69
|
113 |
name: accuracy
|
114 |
source:
|
115 |
+
url: >-
|
116 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
|
117 |
name: Open LLM Leaderboard
|
118 |
+
new_version: sthenno-com/miscii-14b-0218
|
119 |
---
|
120 |
# tempesthenno--nuslerp (BASE MODEL)
|
121 |
|
|
|
248 |
|MATH Lvl 5 (4-Shot)|47.36|
|
249 |
|GPQA (0-shot) |17.00|
|
250 |
|MuSR (0-shot) |14.56|
|
251 |
+
|MMLU-PRO (5-shot) |47.69|
|
|