SteelStorage
/

llama-3-cat-8b-instruct-v1

@@ -1,5 +1,108 @@
 ---
 license: llama3
 ---
 <!DOCTYPE html>
@@ -144,4 +247,17 @@ In humans, protist diseases are caused by protozoa.< / s ><|end_of_text|></code>
     </div>
   </div>
 </body>
-</html>

 ---
 license: llama3
+model-index:
+- name: llama-3-cat-8b-instruct-v1
+  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: 59.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
+      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: 79.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
+      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: 62.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
+      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: 50.8
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
+      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: 75.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
+      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: 60.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
+      name: Open LLM Leaderboard
 ---
 <!DOCTYPE html>
     </div>
   </div>
 </body>
+</html>
+# [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_TheSkullery__llama-3-cat-8b-instruct-v1)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.74|
+|AI2 Reasoning Challenge (25-Shot)|59.04|
+|HellaSwag (10-Shot)              |79.20|
+|MMLU (5-Shot)                    |62.99|
+|TruthfulQA (0-shot)              |50.80|
+|Winogrande (5-shot)              |75.93|
+|GSM8k (5-shot)                   |60.50|