Adding Evaluation Results

README.md

@@ -1,4 +1,8 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
 - bunnycore/Qwen-2.5-7b-rp-lora
@@ -8,11 +12,101 @@ base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
 - fblgit/cybertron-v4-qw7B-MGS
 - bunnycore/Qwen-2.5-7b-rp-lora
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Qwen-2.5-7B-Deep-Stock-v1
+  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: 56.95
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7B-Deep-Stock-v1
+      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: 34.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7B-Deep-Stock-v1
+      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: 25.53
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7B-Deep-Stock-v1
+      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: 3.69
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7B-Deep-Stock-v1
+      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: 9.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7B-Deep-Stock-v1
+      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: 34.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7B-Deep-Stock-v1
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -54,3 +148,17 @@ models:
   - model:           fblgit/cybertron-v4-qw7B-MGS+bunnycore/Qwen-2.5-7b-rp-lora
   - model:           bespokelabs/Bespoke-Stratos-7B
 ```
+
+# [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/bunnycore__Qwen-2.5-7B-Deep-Stock-v1-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.38|
+|IFEval (0-Shot)    |56.95|
+|BBH (3-Shot)       |34.08|
+|MATH Lvl 5 (4-Shot)|25.53|
+|GPQA (0-shot)      | 3.69|
+|MuSR (0-shot)      | 9.96|
+|MMLU-PRO (5-shot)  |34.06|
+