Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
-license: other
 language:
 - en
 - zh
+license: other
 base_model: internlm/internlm2-7b
+model-index:
+- name: internlm2-7b-llama
+  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: 60.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/internlm2-7b-llama
+      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: 80.99
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/internlm2-7b-llama
+      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: 63.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/internlm2-7b-llama
+      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: 54.25
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/internlm2-7b-llama
+      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: 79.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/internlm2-7b-llama
+      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: 62.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/internlm2-7b-llama
+      name: Open LLM Leaderboard
 ---
 # InternLM (but it's Llama)
 
@@ -24,4 +127,17 @@ base_model: internlm/internlm2-7b
 
 [internlm2-7b](https://huggingface.co/internlm/internlm2-base-7b) converted into Llama-format weights.
 
-Subject to internlm's license.
+Subject to internlm's license.
+# [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_chargoddard__internlm2-7b-llama)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.94|
+|AI2 Reasoning Challenge (25-Shot)|60.49|
+|HellaSwag (10-Shot)              |80.99|
+|MMLU (5-Shot)                    |63.16|
+|TruthfulQA (0-shot)              |54.25|
+|Winogrande (5-shot)              |79.87|
+|GSM8k (5-shot)                   |62.85|
+