Adding Evaluation Results

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 library_name: peft
 tags:
 - code
@@ -7,7 +8,109 @@ tags:
 datasets:
 - cognitivecomputations/dolphin-coder
 base_model: codellama/CodeLlama-7b-hf
-license: apache-2.0
+model-index:
+- name: codellama_7b_DolphinCoder
+  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: 41.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Zangs3011/codellama_7b_DolphinCoder
+      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: 65.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Zangs3011/codellama_7b_DolphinCoder
+      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: 38.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Zangs3011/codellama_7b_DolphinCoder
+      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: 35.45
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Zangs3011/codellama_7b_DolphinCoder
+      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: 63.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Zangs3011/codellama_7b_DolphinCoder
+      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: 9.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Zangs3011/codellama_7b_DolphinCoder
+      name: Open LLM Leaderboard
 ---
 
 ### Finetuning Overview:
@@ -42,4 +145,17 @@ With the utilization of [MonsterAPI](https://monsterapi.ai)'s [no-code LLM finet
 ![Train Loss](https://cdn-uploads.huggingface.co/production/uploads/63ba46aa0a9866b28cb19a14/aNujXePogMlJZmoi1Bq56.png)
 
 ---
-license: apache-2.0
+license: apache-2.0
+# [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_Zangs3011__codellama_7b_DolphinCoder)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |42.39|
+|AI2 Reasoning Challenge (25-Shot)|41.98|
+|HellaSwag (10-Shot)              |65.50|
+|MMLU (5-Shot)                    |38.11|
+|TruthfulQA (0-shot)              |35.45|
+|Winogrande (5-shot)              |63.61|
+|GSM8k (5-shot)                   | 9.70|
+