correct open llm leaderboard in model card
Browse files
README.md
CHANGED
@@ -71,7 +71,7 @@ model-index:
|
|
71 |
num_few_shot: 25
|
72 |
metrics:
|
73 |
- type: acc_norm
|
74 |
-
value:
|
75 |
name: normalized accuracy
|
76 |
source:
|
77 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
@@ -87,7 +87,7 @@ model-index:
|
|
87 |
num_few_shot: 10
|
88 |
metrics:
|
89 |
- type: acc_norm
|
90 |
-
value:
|
91 |
name: normalized accuracy
|
92 |
source:
|
93 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
@@ -104,7 +104,7 @@ model-index:
|
|
104 |
num_few_shot: 5
|
105 |
metrics:
|
106 |
- type: acc
|
107 |
-
value: 62.
|
108 |
name: accuracy
|
109 |
source:
|
110 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
@@ -121,7 +121,7 @@ model-index:
|
|
121 |
num_few_shot: 0
|
122 |
metrics:
|
123 |
- type: mc2
|
124 |
-
value:
|
125 |
source:
|
126 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
127 |
name: Open LLM Leaderboard
|
@@ -137,7 +137,7 @@ model-index:
|
|
137 |
num_few_shot: 5
|
138 |
metrics:
|
139 |
- type: acc
|
140 |
-
value: 78.
|
141 |
name: accuracy
|
142 |
source:
|
143 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
@@ -154,7 +154,7 @@ model-index:
|
|
154 |
num_few_shot: 5
|
155 |
metrics:
|
156 |
- type: acc
|
157 |
-
value:
|
158 |
name: accuracy
|
159 |
source:
|
160 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
@@ -366,7 +366,17 @@ model.generate(**gen_input)
|
|
366 |
- https://huggingface.co/bartowski/Einstein-v6-7B-exl2
|
367 |
|
368 |
# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
|
369 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
370 |
|
371 |
# 🤖 Additional information about training
|
372 |
|
@@ -394,17 +404,4 @@ Thanks to all open source AI community.
|
|
394 |
|
395 |
If you would like to support me:
|
396 |
|
397 |
-
[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)
|
398 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
399 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Einstein-v6-7B)
|
400 |
-
|
401 |
-
| Metric |Value|
|
402 |
-
|---------------------------------|----:|
|
403 |
-
|Avg. |65.47|
|
404 |
-
|AI2 Reasoning Challenge (25-Shot)|61.52|
|
405 |
-
|HellaSwag (10-Shot) |80.91|
|
406 |
-
|MMLU (5-Shot) |62.02|
|
407 |
-
|TruthfulQA (0-shot) |51.24|
|
408 |
-
|Winogrande (5-shot) |78.53|
|
409 |
-
|GSM8k (5-shot) |58.61|
|
410 |
-
|
|
|
71 |
num_few_shot: 25
|
72 |
metrics:
|
73 |
- type: acc_norm
|
74 |
+
value: 63.57
|
75 |
name: normalized accuracy
|
76 |
source:
|
77 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
|
|
87 |
num_few_shot: 10
|
88 |
metrics:
|
89 |
- type: acc_norm
|
90 |
+
value: 82.76
|
91 |
name: normalized accuracy
|
92 |
source:
|
93 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
|
|
104 |
num_few_shot: 5
|
105 |
metrics:
|
106 |
- type: acc
|
107 |
+
value: 62.23
|
108 |
name: accuracy
|
109 |
source:
|
110 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
|
|
121 |
num_few_shot: 0
|
122 |
metrics:
|
123 |
- type: mc2
|
124 |
+
value: 52.02
|
125 |
source:
|
126 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
127 |
name: Open LLM Leaderboard
|
|
|
137 |
num_few_shot: 5
|
138 |
metrics:
|
139 |
- type: acc
|
140 |
+
value: 78.61
|
141 |
name: accuracy
|
142 |
source:
|
143 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
|
|
154 |
num_few_shot: 5
|
155 |
metrics:
|
156 |
- type: acc
|
157 |
+
value: 63.53
|
158 |
name: accuracy
|
159 |
source:
|
160 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6-7B
|
|
|
366 |
- https://huggingface.co/bartowski/Einstein-v6-7B-exl2
|
367 |
|
368 |
# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
369 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Einstein-v6-7B)
|
370 |
|
371 |
+
| Metric |Value|
|
372 |
+
|---------------------------------|----:|
|
373 |
+
|Avg. |67.12|
|
374 |
+
|AI2 Reasoning Challenge (25-Shot)|63.57|
|
375 |
+
|HellaSwag (10-Shot) |82.76|
|
376 |
+
|MMLU (5-Shot) |62.23|
|
377 |
+
|TruthfulQA (0-shot) |52.02|
|
378 |
+
|Winogrande (5-shot) |78.61|
|
379 |
+
|GSM8k (5-shot) |63.53|
|
380 |
|
381 |
# 🤖 Additional information about training
|
382 |
|
|
|
404 |
|
405 |
If you would like to support me:
|
406 |
|
407 |
+
[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|