Adding Evaluation Results

README.md

@@ -1,4 +1,9 @@
 ---
+language:
+- zh
+- ja
+- ko
+- tw
 license: apache-2.0
 tags:
 - moe
@@ -8,11 +13,109 @@ tags:
 - MediaTek-Research/Breeze-7B-Instruct-v0.1
 - augmxnt/shisa-7b-v1
 - beomi/OPEN-SOLAR-KO-10.7B
-language:
-- zh
-- ja
-- ko
-- tw
+model-index:
+- name: EastAsia-4x7B-Moe-experiment
+  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: 39.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 48.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 56.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 49.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 0.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      name: Open LLM Leaderboard
 ---
 
 # EastAsia-4x7B-Moe-experiment
@@ -62,4 +165,17 @@ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in
 prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_Heng666__EastAsia-4x7B-Moe-experiment)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |42.12|
+|AI2 Reasoning Challenge (25-Shot)|39.51|
+|HellaSwag (10-Shot)              |48.92|
+|MMLU (5-Shot)                    |56.20|
+|TruthfulQA (0-shot)              |49.83|
+|Winogrande (5-shot)              |58.09|
+|GSM8k (5-shot)                   | 0.15|
+