add evals

README.md

@@ -10,6 +10,101 @@ tags:
 - qwen2
 - trl
 - dpo
+model-index:
+- name: Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
+  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: 41.88
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/j.o.s.i.e.v4o-1.5b-dpo-stage1-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: 17.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/j.o.s.i.e.v4o-1.5b-dpo-stage1-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: 2.49
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/j.o.s.i.e.v4o-1.5b-dpo-stage1-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: 0.11
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/j.o.s.i.e.v4o-1.5b-dpo-stage1-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: 1.44
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/j.o.s.i.e.v4o-1.5b-dpo-stage1-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: 17.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/j.o.s.i.e.v4o-1.5b-dpo-stage1-v1
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -86,3 +181,15 @@ PARAMETER stop <|im_start|>
 PARAMETER stop <|im_end|>
 ```
 
+# [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_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.49|
+|IFEval (0-Shot)    |41.88|
+|BBH (3-Shot)       |17.75|
+|MATH Lvl 5 (4-Shot)| 2.49|
+|GPQA (0-shot)      | 0.11|
+|MuSR (0-shot)      |1.44|
+|MMLU-PRO (5-shot)  |17.28|