Adding Evaluation Results

README.md

@@ -1,9 +1,9 @@
 ---
 license: apache-2.0
-base_model: Qwen/Qwen2-7B
 tags:
 - generated_from_trainer
 - axolotl
+base_model: Qwen/Qwen2-7B
 datasets:
 - cognitivecomputations/Dolphin-2.9
 - teknium/OpenHermes-2.5
@@ -13,6 +13,101 @@ datasets:
 - microsoft/orca-math-word-problems-200k
 - Locutusque/function-calling-chatml
 - internlm/Agent-FLAN
+model-index:
+- name: dolphin-2.9.2-qwen2-7b
+  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: 35.35
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-qwen2-7b
+      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: 27.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-qwen2-7b
+      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: 11.56
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-qwen2-7b
+      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: 5.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-qwen2-7b
+      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: 11.66
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-qwen2-7b
+      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: 33.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-qwen2-7b
+      name: Open LLM Leaderboard
 ---
 
 # Dolphin 2.9.2 Qwen2 7B 🐬
@@ -51,4 +146,17 @@ Dolphin is licensed according to Qwen's tongyi-qianwen license.  We grant permis
 
 ## Evals
 
-![image/png](https://i.ibb.co/0Qw3XtM/file-Oq9-Wr-Qx-H2-Wr8-Eb-Gs15z-Rv-TGe.png)
+![image/png](https://i.ibb.co/0Qw3XtM/file-Oq9-Wr-Qx-H2-Wr8-Eb-Gs15z-Rv-TGe.png)
+# [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_cognitivecomputations__dolphin-2.9.2-qwen2-7b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.96|
+|IFEval (0-Shot)    |35.35|
+|BBH (3-Shot)       |27.91|
+|MATH Lvl 5 (4-Shot)|11.56|
+|GPQA (0-shot)      | 5.37|
+|MuSR (0-shot)      |11.66|
+|MMLU-PRO (5-shot)  |33.90|
+