Adding Evaluation Results

README.md

@@ -1,7 +1,110 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
+model-index:
+- name: firefly-mixtral-8x7b-v0.1
+  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: 68.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=YeungNLP/firefly-mixtral-8x7b-v0.1
+      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: 85.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=YeungNLP/firefly-mixtral-8x7b-v0.1
+      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: 71.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=YeungNLP/firefly-mixtral-8x7b-v0.1
+      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: 55.31
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=YeungNLP/firefly-mixtral-8x7b-v0.1
+      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: 82.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=YeungNLP/firefly-mixtral-8x7b-v0.1
+      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: 59.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=YeungNLP/firefly-mixtral-8x7b-v0.1
+      name: Open LLM Leaderboard
 ---
 
 This model is finetuend based on "mistralai/Mixtral-8x7B-v0.1" with [Firefly](https://github.com/yangjianxin1/Firefly) and 48k data from ultrachat.
@@ -66,3 +169,17 @@ print("Chatbot：{}".format(response))
 
 ```
 
+
+# [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_YeungNLP__firefly-mixtral-8x7b-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.34|
+|AI2 Reasoning Challenge (25-Shot)|68.09|
+|HellaSwag (10-Shot)              |85.76|
+|MMLU (5-Shot)                    |71.49|
+|TruthfulQA (0-shot)              |55.31|
+|Winogrande (5-shot)              |82.08|
+|GSM8k (5-shot)                   |59.29|
+