Adding Evaluation Results (#2)

- Adding Evaluation Results (e063566624794cdc6d0d3e68a3c7790c4dcd532c)

README.md

@@ -1,11 +1,106 @@
 ---
-library_name: transformers
 license: llama3.1
-datasets:
-- netcat420/MFANN
+library_name: transformers
 base_model:
 - netcat420/MFANN-llama3.1-abliterated-SLERP-v3.1
+datasets:
+- netcat420/MFANN
 pipeline_tag: text-generation
+model-index:
+- name: MFANNv0.23
+  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: 31.27
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANNv0.23
+      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: 27.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANNv0.23
+      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: 4.98
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANNv0.23
+      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: 4.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANNv0.23
+      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: 5.5
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANNv0.23
+      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: 26.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=netcat420/MFANNv0.23
+      name: Open LLM Leaderboard
 ---
 standard system prompt: <|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful, respectful and honest assistant. Always answer as helpfully as possible.<|eot_id|>
 
@@ -15,4 +110,17 @@ sampler settings:
 
 context length: 8192 max length: 8192 prompt batch size: 128 temperature: 1 top p: 1 top k: 50 min p: 0.03 repeat penalty tokens: 69 GPU layers (for vulkan offloading in gpt4all): 32 repeat penalty: 1.19
 
-make sure to completely remove the string in "suggest follow-up prompt" to improve generation speed in gpt4all
+make sure to completely remove the string in "suggest follow-up prompt" to improve generation speed in gpt4all
+# [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__MFANNv0.23)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |16.65|
+|IFEval (0-Shot)    |31.27|
+|BBH (3-Shot)       |27.04|
+|MATH Lvl 5 (4-Shot)| 4.98|
+|GPQA (0-shot)      | 4.59|
+|MuSR (0-shot)      | 5.50|
+|MMLU-PRO (5-shot)  |26.53|
+