Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
-library_name: transformers
 license: apache-2.0
+library_name: transformers
 base_model:
 - flammenai/flammen27-mistral-7B
 datasets:
 - flammenai/FlameMix-DPO-v1
 - flammenai/Grill-preprod-v1_chatML
 - flammenai/Grill-preprod-v2_chatML
+model-index:
+- name: Mahou-1.2a-mistral-7B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 68.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=flammenai/Mahou-1.2a-mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 88.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=flammenai/Mahou-1.2a-mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=flammenai/Mahou-1.2a-mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 68.71
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=flammenai/Mahou-1.2a-mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 80.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=flammenai/Mahou-1.2a-mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=flammenai/Mahou-1.2a-mistral-7B
+      name: Open LLM Leaderboard
 ---
 ![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
 
@@ -113,4 +216,17 @@ dpo_trainer = DPOTrainer(
 
 # Fine-tune model with DPO
 dpo_trainer.train()
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_flammenai__Mahou-1.2a-mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.35|
+|AI2 Reasoning Challenge (25-Shot)|68.77|
+|HellaSwag (10-Shot)              |88.14|
+|MMLU (5-Shot)                    |64.73|
+|TruthfulQA (0-shot)              |68.71|
+|Winogrande (5-shot)              |80.11|
+|GSM8k (5-shot)                   |63.61|
+