Adding Evaluation Results (#1)

- Adding Evaluation Results (adc8d1908892facc7d17a6c6421ef5fe4d201ed7)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,8 +1,8 @@
 ---
-license: apache-2.0
 language:
 - en
 - zh
+license: apache-2.0
 tags:
 - Mixtral
 - openbmb/MiniCPM-2B-sft-bf16-llama-format
@@ -13,6 +13,109 @@ tags:
 - MiniCPM
 base_model:
 - openbmb/MiniCPM-2B-sft-bf16-llama-format
+model-index:
+- name: MoECPM-Untrained-4x2b
+  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: 46.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/MoECPM-Untrained-4x2b
+      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: 72.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/MoECPM-Untrained-4x2b
+      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: 53.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/MoECPM-Untrained-4x2b
+      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: 38.41
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/MoECPM-Untrained-4x2b
+      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: 65.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/MoECPM-Untrained-4x2b
+      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: 44.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/MoECPM-Untrained-4x2b
+      name: Open LLM Leaderboard
 ---
 # MoECPM Untrained 4x2b
 
@@ -30,4 +133,17 @@ A MoE model out of 4 MiniCPM-2B-sft models. Intended to be trained. This version
 
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+# [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_Inv__MoECPM-Untrained-4x2b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |53.51|
+|AI2 Reasoning Challenge (25-Shot)|46.76|
+|HellaSwag (10-Shot)              |72.58|
+|MMLU (5-Shot)                    |53.21|
+|TruthfulQA (0-shot)              |38.41|
+|Winogrande (5-shot)              |65.51|
+|GSM8k (5-shot)                   |44.58|
+