Hugging Face's logo

occiglot
/
occiglot-7b-fr-en

Text Generation
Transformers
Safetensors
English
French
mistral
Inference Endpoints
text-generation-inference
Model card Files Community
4
mbrack barthfab commited on
Commit
9fcc6a1
•
1 Parent(s): 2a28d05

clean table (#3)

Browse files

- clean table (93a35c6506748bda473a60261a5eb5d5e7041e11)


Co-authored-by: Fabio Barth <barthfab@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +32 -20
README.md CHANGED
@@ -80,30 +80,42 @@ Currently, we are working on more suitable benchmarks for Spanish, French, Germa
80
  <details>
81
  <summary>Evaluation results</summary>
82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
  ### English
84
 
85
- | | arc_challenge | belebele | hellaswag | mmlu | truthfulqa | avg |
86
- |:-------------------------------------|----------------:|-----------:|------------:|---------:|-------------:|---------:|
87
- | Occiglot-7b-eu5 | 0.530717 | 0.726667 | 0.789882 | 0.531904 | 0.403678 | 0.59657 |
88
- | Occiglot-7b-eu5-instruct | 0.558874 | 0.746667 | 0.799841 | 0.535109 | 0.449034 | 0.617905 |
89
- | Occiglot-7b-fr-en | 0.568259 | 0.771111 | 0.804919 | 0.570716 | 0.394726 | 0.621947 |
90
- | Occiglot-7b-fr-en-instruct | 0.586177 | 0.794444 | 0.808305 | 0.569862 | 0.474064 | 0.646571 |
91
- | Claire-Mistral-7B-0.1 | 0.59727 | 0.817778 | 0.827126 | 0.600912 | 0.415906 | 0.651798 |
92
- | Mistral-7B-v0.1 | 0.612628 | 0.844444 | 0.834097 | 0.624555 | 0.426201 | 0.668385 |
93
- | Mistral-7B-Instruct-v0.2 | 0.637372 | 0.824444 | 0.846345 | 0.59201 | 0.668116 | 0.713657 |
94
-
95
-
96
  ### French
97
 
98
- | | arc_challenge_fr | belebele_fr | hellaswag_fr | mmlu_fr | truthfulqa_fr | avg |
99
- |:-------------------------------------|-------------------:|--------------:|---------------:|----------:|----------------:|---------:|
100
- | Occiglot-7b-eu5 | 0.506416 | 0.675556 | 0.712358 | 0.495684 | 0.23507 | 0.525017 |
101
- | Occiglot-7b-eu5-instruct | 0.541488 | 0.7 | 0.724245 | 0.499122 | 0.306226 | 0.554216 |
102
- | Occiglot-7b-fr-en | 0.532934 | 0.706667 | 0.718891 | 0.51333 | 0.242694 | 0.542903 |
103
- | Occiglot-7b-fr-en-instruct | 0.542344 | 0.752222 | 0.72553 | 0.52051 | 0.29479 | 0.567079 |
104
- | Claire-Mistral-7B-0.1 | 0.486741 | 0.694444 | 0.642964 | 0.479566 | 0.271919 | 0.515127 |
105
- | Mistral-7B-v0.1 | 0.525235 | 0.776667 | 0.66481 | 0.543121 | 0.280813 | 0.558129 |
106
- | Mistral-7B-Instruct-v0.2 | 0.551754 | 0.758889 | 0.67916 | 0.506837 | 0.382465 | 0.575821 |
107
 
108
  </details>
109
 
 
80
  <details>
81
  <summary>Evaluation results</summary>
82
 
83
+ ### All 5 Languages
84
+
85
+ | | avg | arc_challenge | belebele | hellaswag | mmlu | truthfulqa |
86
+ |:---------------------------|---------:|----------------:|-----------:|------------:|---------:|-------------:|
87
+ | Occiglot-7b-eu5 | 0.516895 | 0.508109 | 0.675556 | 0.718963 | 0.402064 | 0.279782 |
88
+ | Occiglot-7b-eu5-instruct | 0.537799 | 0.53632 | 0.691111 | 0.731918 | 0.405198 | 0.32445 |
89
+ | Occiglot-7b-fr-en | 0.509209 | 0.496806 | 0.691333 | 0.667475 | 0.409129 | 0.281303 |
90
+ | Occiglot-7b-fr-en-instruct | 0.52884 | 0.515613 | 0.723333 | 0.67371 | 0.413024 | 0.318521 |
91
+ | Claire-mistral-7b-0.1 | 0.514226 | 0.502773 | 0.705111 | 0.666871 | 0.412128 | 0.284245 |
92
+ | Mistral-7b-v0.1 | 0.547111 | 0.528937 | 0.768444 | 0.682516 | 0.448253 | 0.307403 |
93
+ | Mistral-7b-instruct-v0.2 | 0.56713 | 0.547228 | 0.741111 | 0.69455 | 0.422501 | 0.430262 |
94
+
95
+
96
  ### English
97
 
98
+ | | avg | arc_challenge | belebele | hellaswag | mmlu | truthfulqa |
99
+ |:---------------------------|---------:|----------------:|-----------:|------------:|---------:|-------------:|
100
+ | Occiglot-7b-eu5 | 0.59657 | 0.530717 | 0.726667 | 0.789882 | 0.531904 | 0.403678 |
101
+ | Occiglot-7b-eu5-instruct | 0.617905 | 0.558874 | 0.746667 | 0.799841 | 0.535109 | 0.449 |
102
+ | Occiglot-7b-fr-en | 0.621947 | 0.568259 | 0.771111 | 0.804919 | 0.570716 | 0.394726 |
103
+ | Occiglot-7b-fr-en-instruct | 0.646571 | 0.586177 | 0.794444 | 0.808305 | 0.569862 | 0.474064 |
104
+ | Claire-mistral-7b-0.1 | 0.651798 | 0.59727 | 0.817778 | 0.827126 | 0.600912 | 0.415906 |
105
+ | Mistral-7b-v0.1 | 0.668385 | 0.612628 | 0.844444 | 0.834097 | 0.624555 | 0.426201 |
106
+ | Mistral-7b-instruct-v0.2 | 0.713657 | 0.637372 | 0.824444 | 0.846345 | 0.59201 | 0.668116 |
107
+
 
108
  ### French
109
 
110
+ | | avg | arc_challenge_fr | belebele_fr | hellaswag_fr | mmlu_fr | truthfulqa_fr |
111
+ |:---------------------------|---------:|-------------------:|--------------:|---------------:|----------:|----------------:|
112
+ | Occiglot-7b-eu5 | 0.525017 | 0.506416 | 0.675556 | 0.712358 | 0.495684 | 0.23507 |
113
+ | Occiglot-7b-eu5-instruct | 0.554216 | 0.541488 | 0.7 | 0.724245 | 0.499122 | 0.306226 |
114
+ | Occiglot-7b-fr-en | 0.542903 | 0.532934 | 0.706667 | 0.718891 | 0.51333 | 0.242694 |
115
+ | Occiglot-7b-fr-en-instruct | 0.567079 | 0.542344 | 0.752222 | 0.72553 | 0.52051 | 0.29479 |
116
+ | Claire-mistral-7b-0.1 | 0.515127 | 0.486741 | 0.694444 | 0.642964 | 0.479566 | 0.271919 |
117
+ | Mistral-7b-v0.1 | 0.558129 | 0.525235 | 0.776667 | 0.66481 | 0.543121 | 0.280813 |
118
+ | Mistral-7b-instruct-v0.2 | 0.575821 | 0.551754 | 0.758889 | 0.67916 | 0.506837 | 0.382465 |
119
 
120
  </details>
121