Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
+language:
+- en
+license: bigscience-openrail-m
 library_name: transformers
 tags:
 - code
-license: bigscience-openrail-m
 datasets:
 - tyson0420/stackexchange-4dpo-filby-clang-keywords
-language:
-- en
 metrics:
 - code_eval
+model-index:
+- name: stack_codellama-7b-inst
+  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: 43.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
+      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: 66.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
+      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: 39.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
+      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: 39.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
+      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: 65.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
+      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: 15.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -74,4 +177,17 @@ Evaluating generations...
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [tyson0420]
+- **Developed by:** [tyson0420]
+# [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_tyson0420__stack_codellama-7b-inst)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |44.97|
+|AI2 Reasoning Challenge (25-Shot)|43.52|
+|HellaSwag (10-Shot)              |66.17|
+|MMLU (5-Shot)                    |39.59|
+|TruthfulQA (0-shot)              |39.03|
+|Winogrande (5-shot)              |65.67|
+|GSM8k (5-shot)                   |15.85|
+