Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
+license: apache-2.0
 tags:
 - merge
 - mergekit
 - lazymergekit
-license: apache-2.0
+model-index:
+- name: TriMistral-7B-MODELSTOCK
+  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: 64.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
+      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: 85.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
+      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: 64.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
+      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: 57.24
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
+      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: 78.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
+      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: 52.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
+      name: Open LLM Leaderboard
 ---
 
 # TriMistral-7B-MODELSTOCK
@@ -48,4 +151,17 @@ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7,
 print(outputs[0]["generated_text"])
 ```
 ## 🏆 Evaluation
-Coming Soon
+Coming Soon
+# [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_Muhammad2003__TriMistral-7B-MODELSTOCK)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.15|
+|AI2 Reasoning Challenge (25-Shot)|64.68|
+|HellaSwag (10-Shot)              |85.64|
+|MMLU (5-Shot)                    |64.21|
+|TruthfulQA (0-shot)              |57.24|
+|Winogrande (5-shot)              |78.69|
+|GSM8k (5-shot)                   |52.46|
+