Adding Evaluation Results

README.md

@@ -1,7 +1,110 @@
 ---
+license: openrail
 library_name: peft
 base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
-license: openrail
+model-index:
+- name: ds_diasum_md_mixtral
+  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: 66.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alykassem/ds_diasum_md_mixtral
+      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: 85.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alykassem/ds_diasum_md_mixtral
+      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: 69.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alykassem/ds_diasum_md_mixtral
+      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: 55.72
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alykassem/ds_diasum_md_mixtral
+      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: 80.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alykassem/ds_diasum_md_mixtral
+      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: 53.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alykassem/ds_diasum_md_mixtral
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -202,4 +305,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Framework versions
 
-- PEFT 0.7.1
+- PEFT 0.7.1
+# [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_alykassem__ds_diasum_md_mixtral)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.42|
+|AI2 Reasoning Challenge (25-Shot)|66.30|
+|HellaSwag (10-Shot)              |85.45|
+|MMLU (5-Shot)                    |69.51|
+|TruthfulQA (0-shot)              |55.72|
+|Winogrande (5-shot)              |80.35|
+|GSM8k (5-shot)                   |53.22|
+