Update README.md

README.md

@@ -3,485 +3,483 @@ license: cc-by-nc-4.0
 language:
 - ro
 base_model:
-- mistralai/Mistral-7B-v0.1
+- OpenLLM-Ro/RoMistral-7b-Instruct-2024-10-09
 datasets:
 - OpenLLM-Ro/ro_dpo_helpsteer
-
 model-index:
-    - name: OpenLLM-Ro/RoMistral-7b-Instruct-DPO-2024-10-09
-      results:
-        - task:
-            type: text-generation
-          dataset:
-            name: RoMT-Bench
-            type: RoMT-Bench
-          metrics:
-            - name: Score
-              type: Score
-              value: 5.88
-        - task:
-            type: text-generation
-          dataset:
-            name: RoCulturaBench
-            type: RoCulturaBench
-          metrics:
-            - name: Score
-              type: Score
-              value: 4.72
-        - task:
-            type: text-generation
-          dataset:
-            name: Romanian_Academic_Benchmarks
-            type: Romanian_Academic_Benchmarks
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 51.95
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_arc_challenge
-            type: OpenLLM-Ro/ro_arc_challenge
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 50.73
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_mmlu
-            type: OpenLLM-Ro/ro_mmlu
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 47.88
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_winogrande
-            type: OpenLLM-Ro/ro_winogrande
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 68.41
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_hellaswag
-            type: OpenLLM-Ro/ro_hellaswag
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 62.27
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_gsm8k
-            type: OpenLLM-Ro/ro_gsm8k
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 32.27
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_truthfulqa
-            type: OpenLLM-Ro/ro_truthfulqa
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 50.12
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_binary
-            type: LaRoSeDa_binary
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 82.13
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_multiclass
-            type: LaRoSeDa_multiclass
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 65.24
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_binary_finetuned
-            type: LaRoSeDa_binary_finetuned
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_multiclass_finetuned
-            type: LaRoSeDa_multiclass_finetuned
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_EN-RO
-            type: WMT_EN-RO
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 26.25
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_RO-EN
-            type: WMT_RO-EN
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 6.09
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_EN-RO_finetuned
-            type: WMT_EN-RO_finetuned
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_RO-EN_finetuned
-            type: WMT_RO-EN_finetuned
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD
-            type: XQuAD
-          metrics:
-            - name: Average exact_match
-              type: exact_match
-              value: 23.40
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD
-            type: XQuAD
-          metrics:
-            - name: Average f1
-              type: f1
-              value: 45.80
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_finetuned
-            type: XQuAD_finetuned
-          metrics:
-            - name: Average exact_match
-              type: exact_match
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_finetuned
-            type: XQuAD_finetuned
-          metrics:
-            - name: Average f1
-              type: f1
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: STS
-            type: STS
-          metrics:
-            - name: Average spearman
-              type: spearman
-              value: 77.33
-        - task:
-            type: text-generation
-          dataset:
-            name: STS
-            type: STS
-          metrics:
-            - name: Average pearson
-              type: pearson
-              value: 76.60
-        - task:
-            type: text-generation
-          dataset:
-            name: STS_finetuned
-            type: STS_finetuned
-          metrics:
-            - name: Average spearman
-              type: spearman
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: STS_finetuned
-            type: STS_finetuned
-          metrics:
-            - name: Average pearson
-              type: pearson
-              value: 0.00
-        - task:
-            type: text-generation
-          dataset:
-            name: RoMT-Bench
-            type: RoMT-Bench
-          metrics:
-            - name: First turn
-              type: Score
-              value: 6.44
-            - name: Second turn
-              type: Score
-              value: 5.33
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_arc_challenge
-            type: OpenLLM-Ro/ro_arc_challenge
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 51.67
-            - name: 1-shot 
-              type: accuracy
-              value: 45.59
-            - name: 3-shot 
-              type: accuracy
-              value: 48.24
-            - name: 5-shot 
-              type: accuracy
-              value: 50.21
-            - name: 10-shot 
-              type: accuracy
-              value: 54.07
-            - name: 25-shot 
-              type: accuracy
-              value: 54.58
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_mmlu
-            type: OpenLLM-Ro/ro_mmlu
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 40.86
-            - name: 1-shot 
-              type: accuracy
-              value: 48.67
-            - name: 3-shot 
-              type: accuracy
-              value: 51.26
-            - name: 5-shot 
-              type: accuracy
-              value: 50.75
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_winogrande
-            type: OpenLLM-Ro/ro_winogrande
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 64.80
-            - name: 1-shot 
-              type: accuracy
-              value: 68.19
-            - name: 3-shot 
-              type: accuracy
-              value: 70.09
-            - name: 5-shot 
-              type: accuracy
-              value: 70.56
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_hellaswag
-            type: OpenLLM-Ro/ro_hellaswag
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 61.96
-            - name: 1-shot 
-              type: accuracy
-              value: 60.88
-            - name: 3-shot 
-              type: accuracy
-              value: 61.86
-            - name: 5-shot 
-              type: accuracy
-              value: 62.73
-            - name: 10-shot 
-              type: accuracy
-              value: 63.93
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_gsm8k
-            type: OpenLLM-Ro/ro_gsm8k
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 23.28
-            - name: 1-shot 
-              type: accuracy
-              value: 34.95
-            - name: 3-shot 
-              type: accuracy
-              value: 38.59
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_binary
-            type: LaRoSeDa_binary
-          metrics:
-            - name: 0-shot 
-              type: macro-f1
-              value: 34.36
-            - name: 1-shot 
-              type: macro-f1
-              value: 97.87
-            - name: 3-shot 
-              type: macro-f1
-              value: 98.40
-            - name: 5-shot 
-              type: macro-f1
-              value: 97.90
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_multiclass
-            type: LaRoSeDa_multiclass
-          metrics:
-            - name: 0-shot 
-              type: macro-f1
-              value: 66.17
-            - name: 1-shot 
-              type: macro-f1
-              value: 65.93
-            - name: 3-shot 
-              type: macro-f1
-              value: 61.86
-            - name: 5-shot 
-              type: macro-f1
-              value: 66.99
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_EN-RO
-            type: WMT_EN-RO
-          metrics:
-            - name: 0-shot 
-              type: bleu
-              value: 18.43
-            - name: 1-shot 
-              type: bleu
-              value: 28.25
-            - name: 3-shot 
-              type: bleu
-              value: 29.45
-            - name: 5-shot 
-              type: bleu
-              value: 28.88
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_RO-EN
-            type: WMT_RO-EN
-          metrics:
-            - name: 0-shot 
-              type: bleu
-              value: 2.80
-            - name: 1-shot 
-              type: bleu
-              value: 2.90
-            - name: 3-shot 
-              type: bleu
-              value: 6.63
-            - name: 5-shot 
-              type: bleu
-              value: 12.04
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_EM
-            type: XQuAD_EM
-          metrics:
-            - name: 0-shot 
-              type: exact_match
-              value: 5.04
-            - name: 1-shot 
-              type: exact_match
-              value: 22.44
-            - name: 3-shot 
-              type: exact_match
-              value: 30.42
-            - name: 5-shot 
-              type: exact_match
-              value: 35.71
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_F1
-            type: XQuAD_F1
-          metrics:
-            - name: 0-shot 
-              type: f1
-              value: 23.36
-            - name: 1-shot 
-              type: f1
-              value: 44.63
-            - name: 3-shot 
-              type: f1
-              value: 54.78
-            - name: 5-shot 
-              type: f1
-              value: 60.43
-        - task:
-            type: text-generation
-          dataset:
-            name: STS
-            type: STS
-          metrics:
-            - name: 0-shot 
-              type: spearman
-              value: 73.38
-            - name: 1-shot 
-              type: spearman
-              value: 78.93
-            - name: 3-shot 
-              type: spearman
-              value: 79.68
-        - task:
-            type: text-generation
-          dataset:
-            name: STS
-            type: STS
-          metrics:
-            - name: 0-shot 
-              type: pearson
-              value: 73.93
-            - name: 1-shot 
-              type: pearson
-              value: 77.69
-            - name: 3-shot 
-              type: pearson
-              value: 78.17
-
+- name: OpenLLM-Ro/RoMistral-7b-Instruct-DPO-2024-10-09
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: RoMT-Bench
+      type: RoMT-Bench
+    metrics:
+    - name: Score
+      type: Score
+      value: 5.88
+  - task:
+      type: text-generation
+    dataset:
+      name: RoCulturaBench
+      type: RoCulturaBench
+    metrics:
+    - name: Score
+      type: Score
+      value: 4.72
+  - task:
+      type: text-generation
+    dataset:
+      name: Romanian_Academic_Benchmarks
+      type: Romanian_Academic_Benchmarks
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 51.95
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 50.73
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 47.88
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 68.41
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 62.27
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 32.27
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_truthfulqa
+      type: OpenLLM-Ro/ro_truthfulqa
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 50.12
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 82.13
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 65.24
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary_finetuned
+      type: LaRoSeDa_binary_finetuned
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass_finetuned
+      type: LaRoSeDa_multiclass_finetuned
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 26.25
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 6.09
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO_finetuned
+      type: WMT_EN-RO_finetuned
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN_finetuned
+      type: WMT_RO-EN_finetuned
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average exact_match
+      type: exact_match
+      value: 23.4
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average f1
+      type: f1
+      value: 45.8
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_finetuned
+      type: XQuAD_finetuned
+    metrics:
+    - name: Average exact_match
+      type: exact_match
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_finetuned
+      type: XQuAD_finetuned
+    metrics:
+    - name: Average f1
+      type: f1
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average spearman
+      type: spearman
+      value: 77.33
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average pearson
+      type: pearson
+      value: 76.6
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_finetuned
+      type: STS_finetuned
+    metrics:
+    - name: Average spearman
+      type: spearman
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_finetuned
+      type: STS_finetuned
+    metrics:
+    - name: Average pearson
+      type: pearson
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: RoMT-Bench
+      type: RoMT-Bench
+    metrics:
+    - name: First turn
+      type: Score
+      value: 6.44
+    - name: Second turn
+      type: Score
+      value: 5.33
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 51.67
+    - name: 1-shot
+      type: accuracy
+      value: 45.59
+    - name: 3-shot
+      type: accuracy
+      value: 48.24
+    - name: 5-shot
+      type: accuracy
+      value: 50.21
+    - name: 10-shot
+      type: accuracy
+      value: 54.07
+    - name: 25-shot
+      type: accuracy
+      value: 54.58
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 40.86
+    - name: 1-shot
+      type: accuracy
+      value: 48.67
+    - name: 3-shot
+      type: accuracy
+      value: 51.26
+    - name: 5-shot
+      type: accuracy
+      value: 50.75
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 64.8
+    - name: 1-shot
+      type: accuracy
+      value: 68.19
+    - name: 3-shot
+      type: accuracy
+      value: 70.09
+    - name: 5-shot
+      type: accuracy
+      value: 70.56
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 61.96
+    - name: 1-shot
+      type: accuracy
+      value: 60.88
+    - name: 3-shot
+      type: accuracy
+      value: 61.86
+    - name: 5-shot
+      type: accuracy
+      value: 62.73
+    - name: 10-shot
+      type: accuracy
+      value: 63.93
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 23.28
+    - name: 1-shot
+      type: accuracy
+      value: 34.95
+    - name: 3-shot
+      type: accuracy
+      value: 38.59
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: 0-shot
+      type: macro-f1
+      value: 34.36
+    - name: 1-shot
+      type: macro-f1
+      value: 97.87
+    - name: 3-shot
+      type: macro-f1
+      value: 98.4
+    - name: 5-shot
+      type: macro-f1
+      value: 97.9
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - name: 0-shot
+      type: macro-f1
+      value: 66.17
+    - name: 1-shot
+      type: macro-f1
+      value: 65.93
+    - name: 3-shot
+      type: macro-f1
+      value: 61.86
+    - name: 5-shot
+      type: macro-f1
+      value: 66.99
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: 0-shot
+      type: bleu
+      value: 18.43
+    - name: 1-shot
+      type: bleu
+      value: 28.25
+    - name: 3-shot
+      type: bleu
+      value: 29.45
+    - name: 5-shot
+      type: bleu
+      value: 28.88
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - name: 0-shot
+      type: bleu
+      value: 2.8
+    - name: 1-shot
+      type: bleu
+      value: 2.9
+    - name: 3-shot
+      type: bleu
+      value: 6.63
+    - name: 5-shot
+      type: bleu
+      value: 12.04
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_EM
+      type: XQuAD_EM
+    metrics:
+    - name: 0-shot
+      type: exact_match
+      value: 5.04
+    - name: 1-shot
+      type: exact_match
+      value: 22.44
+    - name: 3-shot
+      type: exact_match
+      value: 30.42
+    - name: 5-shot
+      type: exact_match
+      value: 35.71
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_F1
+      type: XQuAD_F1
+    metrics:
+    - name: 0-shot
+      type: f1
+      value: 23.36
+    - name: 1-shot
+      type: f1
+      value: 44.63
+    - name: 3-shot
+      type: f1
+      value: 54.78
+    - name: 5-shot
+      type: f1
+      value: 60.43
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: 0-shot
+      type: spearman
+      value: 73.38
+    - name: 1-shot
+      type: spearman
+      value: 78.93
+    - name: 3-shot
+      type: spearman
+      value: 79.68
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: 0-shot
+      type: pearson
+      value: 73.93
+    - name: 1-shot
+      type: pearson
+      value: 77.69
+    - name: 3-shot
+      type: pearson
+      value: 78.17
 ---
 
 # Model Card for Model ID