Adding Evaluation Results (#2)

- Adding Evaluation Results (0fcf2f4b9db3126f6fd359dee3f39728fab36c10)

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- O1-OPEN/OpenO1-LLama-8B-v0.1
-- THUDM/LongWriter-llama3.1-8b
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- O1-OPEN/OpenO1-LLama-8B-v0.1
+- THUDM/LongWriter-llama3.1-8b
+model-index:
+- name: longthinker
+  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: 36.09
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=c10x/longthinker
+      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: 28.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=c10x/longthinker
+      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: 15.63
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=c10x/longthinker
+      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: 1.9
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=c10x/longthinker
+      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: 6.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=c10x/longthinker
+      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: 28.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=c10x/longthinker
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -44,3 +138,17 @@ parameters:
   int8_mask: true
 dtype: bfloat16
 ```
+
+# [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_c10x__longthinker)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.47|
+|IFEval (0-Shot)    |36.09|
+|BBH (3-Shot)       |28.42|
+|MATH Lvl 5 (4-Shot)|15.63|
+|GPQA (0-shot)      | 1.90|
+|MuSR (0-shot)      | 6.70|
+|MMLU-PRO (5-shot)  |28.08|
+