Hugging Face's logo

HuggingFaceH4
/
zephyr-7b-beta

Text Generation
Transformers
PyTorch
Safetensors
English
mistral
Generated from Trainer
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
65
clefourrier HF staff Wauplin HF staff commited on
Commit
f4e901c
•
1 Parent(s): 0f17b36

Update Open LLM Leaderboard source urls (#42)

Browse files

- Update Open LLM Leaderboard source urls (8c0add6494cf3115074586ea16d3bace9ac29dd2)


Co-authored-by: Lucain Pouget <Wauplin@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -33,7 +33,7 @@ model-index:
33
  value: 0.6203071672354948
34
  source:
35
  name: Open LLM Leaderboard
36
- url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
37
 
38
  # HellaSwag (10-shot)
39
  - task:
@@ -51,7 +51,7 @@ model-index:
51
  value: 0.8435570603465445
52
  source:
53
  name: Open LLM Leaderboard
54
- url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
55
 
56
  # DROP (3-shot)
57
  - task:
@@ -69,7 +69,7 @@ model-index:
69
  value: 0.09662437080536909
70
  source:
71
  name: Open LLM Leaderboard
72
- url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
73
 
74
  # TruthfulQA (0-shot)
75
  - task:
@@ -87,7 +87,7 @@ model-index:
87
  value: 0.5744916942762855
88
  source:
89
  name: Open LLM Leaderboard
90
- url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
91
 
92
  # GSM8k (5-shot)
93
  - task:
@@ -106,7 +106,7 @@ model-index:
106
  value: 0.12736921910538287
107
  source:
108
  name: Open LLM Leaderboard
109
- url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
110
 
111
  # MMLU (5-Shot)
112
  - task:
@@ -125,7 +125,7 @@ model-index:
125
  value: 0.6107
126
  source:
127
  name: Open LLM Leaderboard
128
- url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
129
 
130
  # Winogrande (5-shot)
131
  - task:
@@ -144,7 +144,7 @@ model-index:
144
  value: 0.7774269928966061
145
  source:
146
  name: Open LLM Leaderboard
147
- url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
148
 
149
  # AlpacaEval (taken from model card)
150
  - task:
 
33
  value: 0.6203071672354948
34
  source:
35
  name: Open LLM Leaderboard
36
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
37
 
38
  # HellaSwag (10-shot)
39
  - task:
 
51
  value: 0.8435570603465445
52
  source:
53
  name: Open LLM Leaderboard
54
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
55
 
56
  # DROP (3-shot)
57
  - task:
 
69
  value: 0.09662437080536909
70
  source:
71
  name: Open LLM Leaderboard
72
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
73
 
74
  # TruthfulQA (0-shot)
75
  - task:
 
87
  value: 0.5744916942762855
88
  source:
89
  name: Open LLM Leaderboard
90
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
91
 
92
  # GSM8k (5-shot)
93
  - task:
 
106
  value: 0.12736921910538287
107
  source:
108
  name: Open LLM Leaderboard
109
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
110
 
111
  # MMLU (5-Shot)
112
  - task:
 
125
  value: 0.6107
126
  source:
127
  name: Open LLM Leaderboard
128
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
129
 
130
  # Winogrande (5-shot)
131
  - task:
 
144
  value: 0.7774269928966061
145
  source:
146
  name: Open LLM Leaderboard
147
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
148
 
149
  # AlpacaEval (taken from model card)
150
  - task: