Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 library_name: transformers
 tags:
 - code
+model-index:
+- name: synapsellm-7b-mistral-v0.5-preview
+  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: 52.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview
+      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: 76.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview
+      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: 54.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview
+      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: 55.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview
+      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: 74.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview
+      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: 22.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview
+      name: Open LLM Leaderboard
 ---
 
 # SynapseLLM:
@@ -72,3 +175,17 @@ This model has some bias areas, discussed below:
 - Model does not have any kind of memory, researchers can experiment feeding memory.
 - Model is trained on different datas, so it can bias information or exclaim itself as gpt model.
 
+
+# [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_WebraftAI__synapsellm-7b-mistral-v0.5-preview)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |56.03|
+|AI2 Reasoning Challenge (25-Shot)|52.73|
+|HellaSwag (10-Shot)              |76.51|
+|MMLU (5-Shot)                    |54.67|
+|TruthfulQA (0-shot)              |55.16|
+|Winogrande (5-shot)              |74.35|
+|GSM8k (5-shot)                   |22.74|
+