Adding Evaluation Results
#2
by
bedio
- opened
README.md
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
library_name: transformers
|
|
|
|
|
3 |
model-index:
|
4 |
- name: ldm_soup_Llama-3.1-8B-Inst
|
5 |
results:
|
@@ -16,8 +21,7 @@ model-index:
|
|
16 |
value: 80.33
|
17 |
name: strict accuracy
|
18 |
source:
|
19 |
-
url:
|
20 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
21 |
name: Open LLM Leaderboard
|
22 |
- task:
|
23 |
type: text-generation
|
@@ -32,8 +36,7 @@ model-index:
|
|
32 |
value: 31.1
|
33 |
name: normalized accuracy
|
34 |
source:
|
35 |
-
url:
|
36 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
37 |
name: Open LLM Leaderboard
|
38 |
- task:
|
39 |
type: text-generation
|
@@ -48,8 +51,7 @@ model-index:
|
|
48 |
value: 11.56
|
49 |
name: exact match
|
50 |
source:
|
51 |
-
url:
|
52 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
53 |
name: Open LLM Leaderboard
|
54 |
- task:
|
55 |
type: text-generation
|
@@ -64,8 +66,7 @@ model-index:
|
|
64 |
value: 5.26
|
65 |
name: acc_norm
|
66 |
source:
|
67 |
-
url:
|
68 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
69 |
name: Open LLM Leaderboard
|
70 |
- task:
|
71 |
type: text-generation
|
@@ -80,8 +81,7 @@ model-index:
|
|
80 |
value: 11.52
|
81 |
name: acc_norm
|
82 |
source:
|
83 |
-
url:
|
84 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
85 |
name: Open LLM Leaderboard
|
86 |
- task:
|
87 |
type: text-generation
|
@@ -98,14 +98,8 @@ model-index:
|
|
98 |
value: 32.07
|
99 |
name: accuracy
|
100 |
source:
|
101 |
-
url:
|
102 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
103 |
name: Open LLM Leaderboard
|
104 |
-
license: apache-2.0
|
105 |
-
language:
|
106 |
-
- en
|
107 |
-
base_model:
|
108 |
-
- meta-llama/Llama-3.1-8B-Instruct
|
109 |
---
|
110 |
|
111 |
# Model Card for DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
@@ -144,4 +138,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
144 |
|MATH Lvl 5 (4-Shot)|11.56|
|
145 |
|GPQA (0-shot) | 5.26|
|
146 |
|MuSR (0-shot) |11.52|
|
147 |
-
|MMLU-PRO (5-shot) |32.07|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
library_name: transformers
|
6 |
+
base_model:
|
7 |
+
- meta-llama/Llama-3.1-8B-Instruct
|
8 |
model-index:
|
9 |
- name: ldm_soup_Llama-3.1-8B-Inst
|
10 |
results:
|
|
|
21 |
value: 80.33
|
22 |
name: strict accuracy
|
23 |
source:
|
24 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
|
|
25 |
name: Open LLM Leaderboard
|
26 |
- task:
|
27 |
type: text-generation
|
|
|
36 |
value: 31.1
|
37 |
name: normalized accuracy
|
38 |
source:
|
39 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
|
|
40 |
name: Open LLM Leaderboard
|
41 |
- task:
|
42 |
type: text-generation
|
|
|
51 |
value: 11.56
|
52 |
name: exact match
|
53 |
source:
|
54 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
|
|
55 |
name: Open LLM Leaderboard
|
56 |
- task:
|
57 |
type: text-generation
|
|
|
66 |
value: 5.26
|
67 |
name: acc_norm
|
68 |
source:
|
69 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
|
|
70 |
name: Open LLM Leaderboard
|
71 |
- task:
|
72 |
type: text-generation
|
|
|
81 |
value: 11.52
|
82 |
name: acc_norm
|
83 |
source:
|
84 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
|
|
85 |
name: Open LLM Leaderboard
|
86 |
- task:
|
87 |
type: text-generation
|
|
|
98 |
value: 32.07
|
99 |
name: accuracy
|
100 |
source:
|
101 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
|
|
102 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
103 |
---
|
104 |
|
105 |
# Model Card for DeepAutoAI/ldm_soup_Llama-3.1-8B-Inst
|
|
|
138 |
|MATH Lvl 5 (4-Shot)|11.56|
|
139 |
|GPQA (0-shot) | 5.26|
|
140 |
|MuSR (0-shot) |11.52|
|
141 |
+
|MMLU-PRO (5-shot) |32.07|
|
142 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
143 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_DeepAutoAI__ldm_soup_Llama-3.1-8B-Inst)
|
144 |
+
|
145 |
+
| Metric |Value|
|
146 |
+
|-------------------|----:|
|
147 |
+
|Avg. |28.64|
|
148 |
+
|IFEval (0-Shot) |80.33|
|
149 |
+
|BBH (3-Shot) |31.10|
|
150 |
+
|MATH Lvl 5 (4-Shot)|11.56|
|
151 |
+
|GPQA (0-shot) | 5.26|
|
152 |
+
|MuSR (0-shot) |11.52|
|
153 |
+
|MMLU-PRO (5-shot) |32.07|
|
154 |
+
|