Adding Evaluation Results (#2)

- Adding Evaluation Results (a4ac66e44661dd994b1b3dcbfe0f953e82e47c16)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,10 +1,113 @@
 ---
-license: apache-2.0
-datasets:
-- malhajar/meditron-tr
 language:
 - tr
 - en
+license: apache-2.0
+datasets:
+- malhajar/meditron-tr
+model-index:
+- name: Mistral-7B-v0.2-meditron-turkish
+  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: 59.56
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/Mistral-7B-v0.2-meditron-turkish
+      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: 81.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/Mistral-7B-v0.2-meditron-turkish
+      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: 60.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/Mistral-7B-v0.2-meditron-turkish
+      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: 66.19
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/Mistral-7B-v0.2-meditron-turkish
+      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: 76.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/Mistral-7B-v0.2-meditron-turkish
+      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: 35.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/Mistral-7B-v0.2-meditron-turkish
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -54,4 +157,17 @@ output = model.generate(inputs=input_ids,max_new_tokens=512,pad_token_id=tokeniz
 response = tokenizer.decode(output[0])
 
 print(response)
-```
+```
+# [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_malhajar__Mistral-7B-v0.2-meditron-turkish)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.34|
+|AI2 Reasoning Challenge (25-Shot)|59.56|
+|HellaSwag (10-Shot)              |81.79|
+|MMLU (5-Shot)                    |60.35|
+|TruthfulQA (0-shot)              |66.19|
+|Winogrande (5-shot)              |76.24|
+|GSM8k (5-shot)                   |35.94|
+