Adding Evaluation Results (#2)

- Adding Evaluation Results (a2c770da351a64d46552b22479dde134ac07f908)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
-- tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
+license: cc-by-nc-4.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: cc-by-nc-4.0
+base_model:
+- grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+- tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
 pipeline_tag: text-generation
+model-index:
+- name: llama-3-Nephilim-v3-8B
+  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: 41.74
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
+      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: 28.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
+      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: 9.14
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
+      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: 6.04
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
+      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: 8.33
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
+      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: 29.02
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
+      name: Open LLM Leaderboard
 ---
 # llama-3-Nephilim-v3-8B
 
@@ -56,3 +151,17 @@ slices:
       weight: 0.1
 
 ```
+
+# [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_grimjim__llama-3-Nephilim-v3-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.54|
+|IFEval (0-Shot)    |41.74|
+|BBH (3-Shot)       |28.96|
+|MATH Lvl 5 (4-Shot)| 9.14|
+|GPQA (0-shot)      | 6.04|
+|MuSR (0-shot)      | 8.33|
+|MMLU-PRO (5-shot)  |29.02|
+