Adding Evaluation Results

README.md

@@ -1,8 +1,103 @@
 ---
-library_name: transformers
 license: apache-2.0
+library_name: transformers
 base_model: 01-ai/Yi-Coder-9B
 pipeline_tag: text-generation
+model-index:
+- name: Yi-Coder-9B-Chat
+  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: 48.17
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=01-ai/Yi-Coder-9B-Chat
+      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: 25.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=01-ai/Yi-Coder-9B-Chat
+      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: 2.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=01-ai/Yi-Coder-9B-Chat
+      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: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=01-ai/Yi-Coder-9B-Chat
+      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: 7.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=01-ai/Yi-Coder-9B-Chat
+      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: 15.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=01-ai/Yi-Coder-9B-Chat
+      name: Open LLM Leaderboard
 ---
 <div align="center">
 
@@ -96,4 +191,17 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(response)
 ```
 
-For getting up and running with Yi-Coder series models quickly, see [Yi-Coder README](https://github.com/01-ai/Yi-Coder).
+For getting up and running with Yi-Coder series models quickly, see [Yi-Coder README](https://github.com/01-ai/Yi-Coder).
+# [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_01-ai__Yi-Coder-9B-Chat)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |16.81|
+|IFEval (0-Shot)    |48.17|
+|BBH (3-Shot)       |25.94|
+|MATH Lvl 5 (4-Shot)| 2.95|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 7.96|
+|MMLU-PRO (5-shot)  |15.84|
+