Hugging Face's logo

nbeerbower
/
Llama3.1-Gutenberg-Doppel-70B

Text Generation
Transformers
Safetensors
llama
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
nbeerbower leaderboard-pr-bot commited on
Commit
f083f3a
•
1 Parent(s): 5de156e

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (4d69e5bad95ff83ed73d05dcba1b2923512850dd)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

Files changed (1) hide show
  1. README.md +110 -2
README.md CHANGED
@@ -1,11 +1,106 @@
1
  ---
 
2
  library_name: transformers
3
  base_model:
4
  - mlabonne/Hermes-3-Llama-3.1-70B-lorablated
5
  datasets:
6
  - jondurbin/gutenberg-dpo-v0.1
7
  - nbeerbower/gutenberg2-dpo
8
- license: llama3.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
  ![image/png](https://huggingface.co/nbeerbower/Mistral-Small-Gutenberg-Doppel-22B/resolve/main/doppel-header?download=true)
11
 
@@ -17,4 +112,17 @@ license: llama3.1
17
 
18
  [ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 2x H100 for 3 epochs.
19
 
20
- Thank you [Schneewolf Labs](https://schneewolflabs.com/) for the compute.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: llama3.1
3
  library_name: transformers
4
  base_model:
5
  - mlabonne/Hermes-3-Llama-3.1-70B-lorablated
6
  datasets:
7
  - jondurbin/gutenberg-dpo-v0.1
8
  - nbeerbower/gutenberg2-dpo
9
+ model-index:
10
+ - name: Llama3.1-Gutenberg-Doppel-70B
11
+ results:
12
+ - task:
13
+ type: text-generation
14
+ name: Text Generation
15
+ dataset:
16
+ name: IFEval (0-Shot)
17
+ type: HuggingFaceH4/ifeval
18
+ args:
19
+ num_few_shot: 0
20
+ metrics:
21
+ - type: inst_level_strict_acc and prompt_level_strict_acc
22
+ value: 70.92
23
+ name: strict accuracy
24
+ source:
25
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama3.1-Gutenberg-Doppel-70B
26
+ name: Open LLM Leaderboard
27
+ - task:
28
+ type: text-generation
29
+ name: Text Generation
30
+ dataset:
31
+ name: BBH (3-Shot)
32
+ type: BBH
33
+ args:
34
+ num_few_shot: 3
35
+ metrics:
36
+ - type: acc_norm
37
+ value: 52.56
38
+ name: normalized accuracy
39
+ source:
40
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama3.1-Gutenberg-Doppel-70B
41
+ name: Open LLM Leaderboard
42
+ - task:
43
+ type: text-generation
44
+ name: Text Generation
45
+ dataset:
46
+ name: MATH Lvl 5 (4-Shot)
47
+ type: hendrycks/competition_math
48
+ args:
49
+ num_few_shot: 4
50
+ metrics:
51
+ - type: exact_match
52
+ value: 13.75
53
+ name: exact match
54
+ source:
55
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama3.1-Gutenberg-Doppel-70B
56
+ name: Open LLM Leaderboard
57
+ - task:
58
+ type: text-generation
59
+ name: Text Generation
60
+ dataset:
61
+ name: GPQA (0-shot)
62
+ type: Idavidrein/gpqa
63
+ args:
64
+ num_few_shot: 0
65
+ metrics:
66
+ - type: acc_norm
67
+ value: 12.64
68
+ name: acc_norm
69
+ source:
70
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama3.1-Gutenberg-Doppel-70B
71
+ name: Open LLM Leaderboard
72
+ - task:
73
+ type: text-generation
74
+ name: Text Generation
75
+ dataset:
76
+ name: MuSR (0-shot)
77
+ type: TAUR-Lab/MuSR
78
+ args:
79
+ num_few_shot: 0
80
+ metrics:
81
+ - type: acc_norm
82
+ value: 22.68
83
+ name: acc_norm
84
+ source:
85
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama3.1-Gutenberg-Doppel-70B
86
+ name: Open LLM Leaderboard
87
+ - task:
88
+ type: text-generation
89
+ name: Text Generation
90
+ dataset:
91
+ name: MMLU-PRO (5-shot)
92
+ type: TIGER-Lab/MMLU-Pro
93
+ config: main
94
+ split: test
95
+ args:
96
+ num_few_shot: 5
97
+ metrics:
98
+ - type: acc
99
+ value: 41.52
100
+ name: accuracy
101
+ source:
102
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama3.1-Gutenberg-Doppel-70B
103
+ name: Open LLM Leaderboard
104
  ---
105
  ![image/png](https://huggingface.co/nbeerbower/Mistral-Small-Gutenberg-Doppel-22B/resolve/main/doppel-header?download=true)
106
 
 
112
 
113
  [ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 2x H100 for 3 epochs.
114
 
115
+ Thank you [Schneewolf Labs](https://schneewolflabs.com/) for the compute.
116
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
117
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbeerbower__Llama3.1-Gutenberg-Doppel-70B)
118
+
119
+ | Metric |Value|
120
+ |-------------------|----:|
121
+ |Avg. |35.68|
122
+ |IFEval (0-Shot) |70.92|
123
+ |BBH (3-Shot) |52.56|
124
+ |MATH Lvl 5 (4-Shot)|13.75|
125
+ |GPQA (0-shot) |12.64|
126
+ |MuSR (0-shot) |22.68|
127
+ |MMLU-PRO (5-shot) |41.52|
128
+