Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
+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
+model-index:
+- name: blossom-v4-yi-34b
+  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: 66.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-yi-34b
+      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: 84.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-yi-34b
+      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: 74.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-yi-34b
+      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: 57.89
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-yi-34b
+      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: 82.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-yi-34b
+      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: 64.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azure99/blossom-v4-yi-34b
+      name: Open LLM Leaderboard
 ---
 # **BLOSSOM-v4-yi-34b**
 
@@ -41,4 +144,17 @@ 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 `<|endoftext|>`.
+Note: At the end of the Bot's output in the historical conversation, append a `<|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-yi-34b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.67|
+|AI2 Reasoning Challenge (25-Shot)|66.81|
+|HellaSwag (10-Shot)              |84.44|
+|MMLU (5-Shot)                    |74.34|
+|TruthfulQA (0-shot)              |57.89|
+|Winogrande (5-shot)              |82.40|
+|GSM8k (5-shot)                   |64.14|
+