Commit
•
c131862
1
Parent(s):
c0b08af
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (c77f2be6660225ca668e552e8ffe33f372295ee0)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
@@ -12,6 +12,109 @@ base_model:
|
|
12 |
- mlabonne/NeuralHermes-2.5-Mistral-7B
|
13 |
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
|
14 |
- Open-Orca/Mistral-7B-OpenOrca
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
---
|
16 |
|
17 |
# Darewin-7B-v2
|
@@ -90,4 +193,17 @@ pipeline = transformers.pipeline(
|
|
90 |
|
91 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
92 |
print(outputs[0]["generated_text"])
|
93 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
- mlabonne/NeuralHermes-2.5-Mistral-7B
|
13 |
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
|
14 |
- Open-Orca/Mistral-7B-OpenOrca
|
15 |
+
model-index:
|
16 |
+
- name: Darewin-7B-v2
|
17 |
+
results:
|
18 |
+
- task:
|
19 |
+
type: text-generation
|
20 |
+
name: Text Generation
|
21 |
+
dataset:
|
22 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
23 |
+
type: ai2_arc
|
24 |
+
config: ARC-Challenge
|
25 |
+
split: test
|
26 |
+
args:
|
27 |
+
num_few_shot: 25
|
28 |
+
metrics:
|
29 |
+
- type: acc_norm
|
30 |
+
value: 62.63
|
31 |
+
name: normalized accuracy
|
32 |
+
source:
|
33 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
|
34 |
+
name: Open LLM Leaderboard
|
35 |
+
- task:
|
36 |
+
type: text-generation
|
37 |
+
name: Text Generation
|
38 |
+
dataset:
|
39 |
+
name: HellaSwag (10-Shot)
|
40 |
+
type: hellaswag
|
41 |
+
split: validation
|
42 |
+
args:
|
43 |
+
num_few_shot: 10
|
44 |
+
metrics:
|
45 |
+
- type: acc_norm
|
46 |
+
value: 78.28
|
47 |
+
name: normalized accuracy
|
48 |
+
source:
|
49 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
|
50 |
+
name: Open LLM Leaderboard
|
51 |
+
- task:
|
52 |
+
type: text-generation
|
53 |
+
name: Text Generation
|
54 |
+
dataset:
|
55 |
+
name: MMLU (5-Shot)
|
56 |
+
type: cais/mmlu
|
57 |
+
config: all
|
58 |
+
split: test
|
59 |
+
args:
|
60 |
+
num_few_shot: 5
|
61 |
+
metrics:
|
62 |
+
- type: acc
|
63 |
+
value: 53.01
|
64 |
+
name: accuracy
|
65 |
+
source:
|
66 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
|
67 |
+
name: Open LLM Leaderboard
|
68 |
+
- task:
|
69 |
+
type: text-generation
|
70 |
+
name: Text Generation
|
71 |
+
dataset:
|
72 |
+
name: TruthfulQA (0-shot)
|
73 |
+
type: truthful_qa
|
74 |
+
config: multiple_choice
|
75 |
+
split: validation
|
76 |
+
args:
|
77 |
+
num_few_shot: 0
|
78 |
+
metrics:
|
79 |
+
- type: mc2
|
80 |
+
value: 50.99
|
81 |
+
source:
|
82 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
|
83 |
+
name: Open LLM Leaderboard
|
84 |
+
- task:
|
85 |
+
type: text-generation
|
86 |
+
name: Text Generation
|
87 |
+
dataset:
|
88 |
+
name: Winogrande (5-shot)
|
89 |
+
type: winogrande
|
90 |
+
config: winogrande_xl
|
91 |
+
split: validation
|
92 |
+
args:
|
93 |
+
num_few_shot: 5
|
94 |
+
metrics:
|
95 |
+
- type: acc
|
96 |
+
value: 73.95
|
97 |
+
name: accuracy
|
98 |
+
source:
|
99 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
|
100 |
+
name: Open LLM Leaderboard
|
101 |
+
- task:
|
102 |
+
type: text-generation
|
103 |
+
name: Text Generation
|
104 |
+
dataset:
|
105 |
+
name: GSM8k (5-shot)
|
106 |
+
type: gsm8k
|
107 |
+
config: main
|
108 |
+
split: test
|
109 |
+
args:
|
110 |
+
num_few_shot: 5
|
111 |
+
metrics:
|
112 |
+
- type: acc
|
113 |
+
value: 19.18
|
114 |
+
name: accuracy
|
115 |
+
source:
|
116 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
|
117 |
+
name: Open LLM Leaderboard
|
118 |
---
|
119 |
|
120 |
# Darewin-7B-v2
|
|
|
193 |
|
194 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
195 |
print(outputs[0]["generated_text"])
|
196 |
+
```
|
197 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
198 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mlabonne__Darewin-7B-v2)
|
199 |
+
|
200 |
+
| Metric |Value|
|
201 |
+
|---------------------------------|----:|
|
202 |
+
|Avg. |56.34|
|
203 |
+
|AI2 Reasoning Challenge (25-Shot)|62.63|
|
204 |
+
|HellaSwag (10-Shot) |78.28|
|
205 |
+
|MMLU (5-Shot) |53.01|
|
206 |
+
|TruthfulQA (0-shot) |50.99|
|
207 |
+
|Winogrande (5-shot) |73.95|
|
208 |
+
|GSM8k (5-shot) |19.18|
|
209 |
+
|