Adding Evaluation Results

README.md

@@ -2,6 +2,109 @@
 license: other
 license_name: deepseek-license
 license_link: LICENSE
+model-index:
+- name: deepseek-coder-6.7b-base
+  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: 37.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-coder-6.7b-base
+      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: 53.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-coder-6.7b-base
+      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: 38.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-coder-6.7b-base
+      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: 40.28
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-coder-6.7b-base
+      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: 58.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-coder-6.7b-base
+      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: 17.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-coder-6.7b-base
+      name: Open LLM Leaderboard
 ---
 
 <p align="center">
@@ -164,3 +267,17 @@ See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/
 ### 5. Contact
 
 If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
+
+# [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_deepseek-ai__deepseek-coder-6.7b-base)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |40.87|
+|AI2 Reasoning Challenge (25-Shot)|37.03|
+|HellaSwag (10-Shot)              |53.46|
+|MMLU (5-Shot)                    |38.39|
+|TruthfulQA (0-shot)              |40.28|
+|Winogrande (5-shot)              |58.09|
+|GSM8k (5-shot)                   |17.97|
+