Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
+language:
+- zh
+- en
 license: apache-2.0
 datasets:
 - Azure99/blossom-chat-v2
 - Azure99/blossom-math-v3
 - Azure99/blossom-wizard-v2
 - Azure99/blossom-orca-v2
-language:
-- zh
-- en
 pipeline_tag: text-generation
+model-index:
+- name: blossom-v4-qwen1_5-7b
+  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: 54.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-qwen1_5-7b
+      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: 76.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-qwen1_5-7b
+      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: 60.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-qwen1_5-7b
+      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: 53.69
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-qwen1_5-7b
+      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: 71.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-qwen1_5-7b
+      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: 56.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-qwen1_5-7b
+      name: Open LLM Leaderboard
 ---
 # **BLOSSOM-v4-qwen1_5-7b**
 
@@ -42,4 +145,17 @@ A chat between a human and an artificial intelligence bot. The bot gives helpful
 |Bot|: 
 ```
 
-注意：在历史对话的Bot输出结尾，拼接一个<|endoftext|>
+注意：在历史对话的Bot输出结尾，拼接一个<|endoftext|>
+# [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_Azure99__blossom-v4-qwen1_5-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.11|
+|AI2 Reasoning Challenge (25-Shot)|54.44|
+|HellaSwag (10-Shot)              |76.11|
+|MMLU (5-Shot)                    |60.43|
+|TruthfulQA (0-shot)              |53.69|
+|Winogrande (5-shot)              |71.27|
+|GSM8k (5-shot)                   |56.71|
+