Adding Evaluation Results (#1)

- Adding Evaluation Results (5c8d405aaed756ffd2eee1a8c2f306a69d239db7)


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

README.md

@@ -7,6 +7,109 @@ tags:
 - mlabonne/Monarch-7B
 - paulml/OGNO-7B
 - AbacusResearch/haLLAwa3
+model-index:
+- name: haLLawa4-7b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 71.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/haLLawa4-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 88.36
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/haLLawa4-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/haLLawa4-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 74.27
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/haLLawa4-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 82.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/haLLawa4-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 70.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/haLLawa4-7b
+      name: Open LLM Leaderboard
 ---
 
 # haLLawa4-7b
@@ -43,4 +146,17 @@ parameters:
   int8_mask: true
 dtype: bfloat16
 random_seed: 0
-\```
+\```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_AbacusResearch__haLLawa4-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.25|
+|AI2 Reasoning Challenge (25-Shot)|71.50|
+|HellaSwag (10-Shot)              |88.36|
+|MMLU (5-Shot)                    |64.49|
+|TruthfulQA (0-shot)              |74.27|
+|Winogrande (5-shot)              |82.40|
+|GSM8k (5-shot)                   |70.51|
+