Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-base_model:
-- meta-llama/Meta-Llama-3-8B-Instruct
+license: llama3
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
+model-index:
+- name: Llama-3-15B-Instruct-zeroed
+  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: 61.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elinas/Llama-3-15B-Instruct-zeroed
+      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: 78.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elinas/Llama-3-15B-Instruct-zeroed
+      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: 67.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elinas/Llama-3-15B-Instruct-zeroed
+      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: 52.46
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elinas/Llama-3-15B-Instruct-zeroed
+      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: 74.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elinas/Llama-3-15B-Instruct-zeroed
+      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: 70.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elinas/Llama-3-15B-Instruct-zeroed
+      name: Open LLM Leaderboard
 ---
 # Llama-3-15B-Instruct-zeroed
 
@@ -60,4 +163,17 @@ slices:
 - sources:
   - layer_range: [24, 32]
     model: meta-llama/Meta-Llama-3-8B-Instruct
-```
+```
+# [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_elinas__Llama-3-15B-Instruct-zeroed)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.75|
+|AI2 Reasoning Challenge (25-Shot)|61.69|
+|HellaSwag (10-Shot)              |78.64|
+|MMLU (5-Shot)                    |67.97|
+|TruthfulQA (0-shot)              |52.46|
+|Winogrande (5-shot)              |74.98|
+|GSM8k (5-shot)                   |70.74|
+