Adding Evaluation Results

README.md

@@ -2,6 +2,109 @@
 license: other
 license_name: deepseek
 license_link: LICENSE
+model-index:
+- name: deepseek-llm-67b-chat
+  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: 67.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-llm-67b-chat
+      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: 86.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-llm-67b-chat
+      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: 72.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-llm-67b-chat
+      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: 55.85
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-llm-67b-chat
+      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: 84.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-llm-67b-chat
+      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: 63.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=deepseek-ai/deepseek-llm-67b-chat
+      name: Open LLM Leaderboard
 ---
 
 <p align="center">
@@ -69,3 +172,17 @@ See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-LLM/blob/main/LI
 
 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-llm-67b-chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.79|
+|AI2 Reasoning Challenge (25-Shot)|67.75|
+|HellaSwag (10-Shot)              |86.82|
+|MMLU (5-Shot)                    |72.42|
+|TruthfulQA (0-shot)              |55.85|
+|Winogrande (5-shot)              |84.21|
+|GSM8k (5-shot)                   |63.68|
+