Adding Evaluation Results

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- netcat420/MFANNv0.19
-- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- netcat420/MFANNv0.19
+- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
+model-index:
+- name: MFANN-llama3.1-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: 44.29
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANN-llama3.1-abliterated-v2
+      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: 27.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANN-llama3.1-abliterated-v2
+      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: 6.57
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANN-llama3.1-abliterated-v2
+      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: 5.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANN-llama3.1-abliterated-v2
+      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: 6.2
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANN-llama3.1-abliterated-v2
+      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: 27.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANN-llama3.1-abliterated-v2
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -45,3 +139,17 @@ parameters:
     - value: 0.5
 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_netcat420__MFANN-llama3.1-abliterated-v2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.63|
+|IFEval (0-Shot)    |44.29|
+|BBH (3-Shot)       |27.35|
+|MATH Lvl 5 (4-Shot)| 6.57|
+|GPQA (0-shot)      | 5.70|
+|MuSR (0-shot)      | 6.20|
+|MMLU-PRO (5-shot)  |27.67|
+