Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
+language:
+- zh
+- en
 license: apache-2.0
 datasets:
 - Azure99/blossom-chat-v3
 - Azure99/blossom-math-v4
 - Azure99/blossom-wizard-v3
 - Azure99/blossom-orca-v3
-language:
-- zh
-- en
+model-index:
+- name: blossom-v5-llama3-8b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 43.43
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Azure99/blossom-v5-llama3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 18.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Azure99/blossom-v5-llama3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Azure99/blossom-v5-llama3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 2.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Azure99/blossom-v5-llama3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.31
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Azure99/blossom-v5-llama3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 13.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Azure99/blossom-v5-llama3-8b
+      name: Open LLM Leaderboard
 ---
 # **BLOSSOM-v5-llama3-8b**
 
@@ -45,4 +140,17 @@ A chat between a human and an artificial intelligence bot. The bot gives helpful
 |Bot|: 
 ```
 
-Note: At the end of the Bot's output in the historical conversation, append a `<|end_of_text|>`.
+Note: At the end of the Bot's output in the historical conversation, append a `<|end_of_text|>`.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Azure99__blossom-v5-llama3-8b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |14.41|
+|IFEval (0-Shot)    |43.43|
+|BBH (3-Shot)       |18.31|
+|MATH Lvl 5 (4-Shot)| 4.00|
+|GPQA (0-shot)      | 2.01|
+|MuSR (0-shot)      | 5.31|
+|MMLU-PRO (5-shot)  |13.40|
+