Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
-base_model: Qwen/Qwen2.5-7B-Instruct
 license: apache-2.0
 tags:
 - axolotl
 - dpo
 - trl
 - generated_from_trainer
+base_model: Qwen/Qwen2.5-7B-Instruct
+model-index:
+- name: Humanish-Qwen2.5-7B-Instruct
+  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: 72.84
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Qwen2.5-7B-Instruct
+      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: 34.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Qwen2.5-7B-Instruct
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Qwen2.5-7B-Instruct
+      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: 6.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Qwen2.5-7B-Instruct
+      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: 8.42
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Qwen2.5-7B-Instruct
+      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: 37.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Qwen2.5-7B-Instruct
+      name: Open LLM Leaderboard
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -141,4 +236,17 @@ The following hyperparameters were used during training:
 - Transformers 4.45.1
 - Pytorch 2.3.1+cu121
 - Datasets 2.21.0
-- Tokenizers 0.20.0
+- Tokenizers 0.20.0
+# [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_HumanLLMs__Humanish-Qwen2.5-7B-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.67|
+|IFEval (0-Shot)    |72.84|
+|BBH (3-Shot)       |34.48|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 6.49|
+|MuSR (0-shot)      | 8.42|
+|MMLU-PRO (5-shot)  |37.76|
+