Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 tags:
 - merge
 base_model:
 - Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp
 - EmbeddedLLM/Mistral-7B-Merge-14-v0.3
+model-index:
+- name: Mistral-7B-Merge-14-v0.4
+  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: 66.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.4
+      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: 86.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.4
+      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: 65.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.4
+      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: 58.25
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.4
+      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: 80.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.4
+      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: 70.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.4
+      name: Open LLM Leaderboard
 ---
 
 # Model Description
@@ -57,4 +160,17 @@ tokenizer_source: base
 embed_slerp: 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-v0.4)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.19|
+|AI2 Reasoning Challenge (25-Shot)|66.81|
+|HellaSwag (10-Shot)              |86.15|
+|MMLU (5-Shot)                    |65.10|
+|TruthfulQA (0-shot)              |58.25|
+|Winogrande (5-shot)              |80.03|
+|GSM8k (5-shot)                   |70.81|
+