Adding Evaluation Results

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- Qwen/Qwen2.5-14B-Instruct
-- Lambent/qwen2.5-lumen-rebased-14B
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- Qwen/Qwen2.5-14B-Instruct
+- Lambent/qwen2.5-lumen-rebased-14B
+model-index:
+- name: qwen2.5-reinstruct-alternate-lumen-14B
+  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: 47.94
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
+      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: 48.99
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
+      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: 19.79
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
+      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: 16.89
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
+      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: 19.62
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
+      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: 48.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
+      name: Open LLM Leaderboard
 ---
 # qwenreinstruct
 
@@ -52,3 +146,17 @@ tokenizer_source: base
 
 
 ```
+
+# [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_Lambent__qwen2.5-reinstruct-alternate-lumen-14B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |33.66|
+|IFEval (0-Shot)    |47.94|
+|BBH (3-Shot)       |48.99|
+|MATH Lvl 5 (4-Shot)|19.79|
+|GPQA (0-shot)      |16.89|
+|MuSR (0-shot)      |19.62|
+|MMLU-PRO (5-shot)  |48.76|
+