Adding Evaluation Results (#1)

- Adding Evaluation Results (74476113910aaa2e3bbfd65a80738ac29ca7b564)


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

README.md

@@ -3,6 +3,101 @@ library_name: transformers
 tags:
 - trl
 - sft
+model-index:
+- name: llama-3.1-8B-Galore-openassistant-guanaco
+  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: 26.35
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
+      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: 31.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
+      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: 4.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
+      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: 6.71
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
+      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: 14.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
+      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: 24.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -18,3 +113,17 @@ tags:
 ### Training Procedure
 
 Trained with SFTTrainer with Galore quantization.
+
+# [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_BlackBeenie__llama-3.1-8B-Galore-openassistant-guanaco)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.07|
+|IFEval (0-Shot)    |26.35|
+|BBH (3-Shot)       |31.44|
+|MATH Lvl 5 (4-Shot)| 4.83|
+|GPQA (0-shot)      | 6.71|
+|MuSR (0-shot)      |14.58|
+|MMLU-PRO (5-shot)  |24.52|
+