Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
+tags:
+- not-for-all-audiences
 base_model:
 - Qwen/Qwen2.5-7B
 pipeline_tag: text-generation
-tags:
-- not-for-all-audiences
-language:
-- en
-library_name: transformers
+model-index:
+- name: Qwen-7B-nerd-uncensored-v1.0
+  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: 61.51
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jeffmeloy/Qwen-7B-nerd-uncensored-v1.0
+      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: 34.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jeffmeloy/Qwen-7B-nerd-uncensored-v1.0
+      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: 24.7
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jeffmeloy/Qwen-7B-nerd-uncensored-v1.0
+      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: 10.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jeffmeloy/Qwen-7B-nerd-uncensored-v1.0
+      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: 18.91
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jeffmeloy/Qwen-7B-nerd-uncensored-v1.0
+      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: 37.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jeffmeloy/Qwen-7B-nerd-uncensored-v1.0
+      name: Open LLM Leaderboard
 ---
 
 ## Model Description
@@ -119,4 +214,17 @@ models_dir: "./input_models/"
 
 output_dir: "./merged_model/"
 
-metric_dir: "./metrics/"
+metric_dir: "./metrics/"
+# [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_jeffmeloy__Qwen-7B-nerd-uncensored-v1.0)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |31.18|
+|IFEval (0-Shot)    |61.51|
+|BBH (3-Shot)       |34.19|
+|MATH Lvl 5 (4-Shot)|24.70|
+|GPQA (0-shot)      |10.40|
+|MuSR (0-shot)      |18.91|
+|MMLU-PRO (5-shot)  |37.36|
+