Files changed (1) hide show
  1. README.md +116 -8
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- license: apache-2.0
3
  language:
4
  - en
5
- pipeline_tag: text-generation
 
6
  tags:
7
  - chat
8
  - qwen
@@ -13,17 +13,112 @@ tags:
13
  - HelpSteer2
14
  - Orca
15
  - SlimOrca
16
- library_name: transformers
17
- inference: false
18
- model_creator: MaziyarPanahi
19
- quantized_by: MaziyarPanahi
20
  base_model: Qwen/Qwen2-7B
21
- model_name: calme-2.8-qwen2-7b
22
  datasets:
23
  - nvidia/HelpSteer2
24
  - teknium/OpenHermes-2.5
25
  - microsoft/orca-math-word-problems-200k
26
  - Open-Orca/SlimOrca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  ---
28
 
29
  <img src="./qwen2-fine-tunes-maziyar-panahi.webp" alt="Qwen2 fine-tune" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -78,4 +173,17 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
78
 
79
  tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
80
  model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
81
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
  tags:
7
  - chat
8
  - qwen
 
13
  - HelpSteer2
14
  - Orca
15
  - SlimOrca
 
 
 
 
16
  base_model: Qwen/Qwen2-7B
 
17
  datasets:
18
  - nvidia/HelpSteer2
19
  - teknium/OpenHermes-2.5
20
  - microsoft/orca-math-word-problems-200k
21
  - Open-Orca/SlimOrca
22
+ model_name: calme-2.8-qwen2-7b
23
+ pipeline_tag: text-generation
24
+ inference: false
25
+ model_creator: MaziyarPanahi
26
+ quantized_by: MaziyarPanahi
27
+ model-index:
28
+ - name: Qwen2-7B-Instruct-v0.8
29
+ results:
30
+ - task:
31
+ type: text-generation
32
+ name: Text Generation
33
+ dataset:
34
+ name: IFEval (0-Shot)
35
+ type: HuggingFaceH4/ifeval
36
+ args:
37
+ num_few_shot: 0
38
+ metrics:
39
+ - type: inst_level_strict_acc and prompt_level_strict_acc
40
+ value: 27.75
41
+ name: strict accuracy
42
+ source:
43
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-7B-Instruct-v0.8
44
+ name: Open LLM Leaderboard
45
+ - task:
46
+ type: text-generation
47
+ name: Text Generation
48
+ dataset:
49
+ name: BBH (3-Shot)
50
+ type: BBH
51
+ args:
52
+ num_few_shot: 3
53
+ metrics:
54
+ - type: acc_norm
55
+ value: 25.53
56
+ name: normalized accuracy
57
+ source:
58
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-7B-Instruct-v0.8
59
+ name: Open LLM Leaderboard
60
+ - task:
61
+ type: text-generation
62
+ name: Text Generation
63
+ dataset:
64
+ name: MATH Lvl 5 (4-Shot)
65
+ type: hendrycks/competition_math
66
+ args:
67
+ num_few_shot: 4
68
+ metrics:
69
+ - type: exact_match
70
+ value: 15.63
71
+ name: exact match
72
+ source:
73
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-7B-Instruct-v0.8
74
+ name: Open LLM Leaderboard
75
+ - task:
76
+ type: text-generation
77
+ name: Text Generation
78
+ dataset:
79
+ name: GPQA (0-shot)
80
+ type: Idavidrein/gpqa
81
+ args:
82
+ num_few_shot: 0
83
+ metrics:
84
+ - type: acc_norm
85
+ value: 5.82
86
+ name: acc_norm
87
+ source:
88
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-7B-Instruct-v0.8
89
+ name: Open LLM Leaderboard
90
+ - task:
91
+ type: text-generation
92
+ name: Text Generation
93
+ dataset:
94
+ name: MuSR (0-shot)
95
+ type: TAUR-Lab/MuSR
96
+ args:
97
+ num_few_shot: 0
98
+ metrics:
99
+ - type: acc_norm
100
+ value: 12.06
101
+ name: acc_norm
102
+ source:
103
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-7B-Instruct-v0.8
104
+ name: Open LLM Leaderboard
105
+ - task:
106
+ type: text-generation
107
+ name: Text Generation
108
+ dataset:
109
+ name: MMLU-PRO (5-shot)
110
+ type: TIGER-Lab/MMLU-Pro
111
+ config: main
112
+ split: test
113
+ args:
114
+ num_few_shot: 5
115
+ metrics:
116
+ - type: acc
117
+ value: 28.51
118
+ name: accuracy
119
+ source:
120
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-7B-Instruct-v0.8
121
+ name: Open LLM Leaderboard
122
  ---
123
 
124
  <img src="./qwen2-fine-tunes-maziyar-panahi.webp" alt="Qwen2 fine-tune" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
 
173
 
174
  tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
175
  model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
176
+ ```
177
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
178
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Qwen2-7B-Instruct-v0.8)
179
+
180
+ | Metric |Value|
181
+ |-------------------|----:|
182
+ |Avg. |19.22|
183
+ |IFEval (0-Shot) |27.75|
184
+ |BBH (3-Shot) |25.53|
185
+ |MATH Lvl 5 (4-Shot)|15.63|
186
+ |GPQA (0-shot) | 5.82|
187
+ |MuSR (0-shot) |12.06|
188
+ |MMLU-PRO (5-shot) |28.51|
189
+