Adding Evaluation Results

README.md

@@ -1,7 +1,7 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 tags:
 - merge
 base_model:
@@ -19,6 +19,109 @@ base_model:
 - teknium/OpenHermes-2.5-Mistral-7B
 - Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
 - mlabonne/NeuralHermes-2.5-Mistral-7B
+model-index:
+- name: Mistral-7B-Merge-14-v0.3
+  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: 65.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3
+      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: 85.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3
+      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: 64.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3
+      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: 57.8
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3
+      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: 78.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3
+      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: 66.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3
+      name: Open LLM Leaderboard
 ---
 
 # Update 2024-01-03
@@ -142,4 +245,17 @@ parameters:
   int8_mask: true
 dtype: bfloat16
 
-```
+```
+# [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_EmbeddedLLM__Mistral-7B-Merge-14-v0.3)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.66|
+|AI2 Reasoning Challenge (25-Shot)|65.96|
+|HellaSwag (10-Shot)              |85.29|
+|MMLU (5-Shot)                    |64.35|
+|TruthfulQA (0-shot)              |57.80|
+|Winogrande (5-shot)              |78.30|
+|GSM8k (5-shot)                   |66.26|
+