Adding Evaluation Results

README.md

@@ -1,12 +1,107 @@
 ---
-library_name: transformers
 license: llama3
+library_name: transformers
 base_model:
 - nbeerbower/llama-3-Stheno-Mahou-8B
 datasets:
 - flammenai/FlameMix-DPO-v1
 - flammenai/Grill-preprod-v1_chatML
 - flammenai/Grill-preprod-v2_chatML
+model-index:
+- name: Mahou-1.2a-llama3-8B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 50.93
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.2a-llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 28.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.2a-llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 7.55
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.2a-llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.2a-llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 6.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.2a-llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 31.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.2a-llama3-8B
+      name: Open LLM Leaderboard
 ---
 ![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
 
@@ -111,4 +206,17 @@ dpo_trainer = DPOTrainer(
 
 # Fine-tune model with DPO
 dpo_trainer.train()
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_flammenai__Mahou-1.2a-llama3-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.65|
+|IFEval (0-Shot)    |50.93|
+|BBH (3-Shot)       |28.97|
+|MATH Lvl 5 (4-Shot)| 7.55|
+|GPQA (0-shot)      | 5.15|
+|MuSR (0-shot)      | 6.02|
+|MMLU-PRO (5-shot)  |31.30|
+