Adding Evaluation Results

README.md

@@ -1,4 +1,5 @@
 ---
+license: llama3
 tags:
 - merge
 - mergekit
@@ -54,7 +55,109 @@ base_model:
 - NousResearch/Meta-Llama-3-8B
 - ryan0712/llama-3-8b-slow-DUS-random-layer-method2
 - NousResearch/Meta-Llama-3-8B
-license: llama3
+model-index:
+- name: llama-3-8b-slow-DUS-random-method2
+  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: 39.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ryan0712/llama-3-8b-slow-DUS-random-method2
+      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: 63.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ryan0712/llama-3-8b-slow-DUS-random-method2
+      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: 30.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ryan0712/llama-3-8b-slow-DUS-random-method2
+      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: 37.04
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ryan0712/llama-3-8b-slow-DUS-random-method2
+      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: 60.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ryan0712/llama-3-8b-slow-DUS-random-method2
+      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: 0.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ryan0712/llama-3-8b-slow-DUS-random-method2
+      name: Open LLM Leaderboard
 ---
 
 # llama-3-8b-slow-DUS-random-method2
@@ -333,4 +436,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_ryan0712__llama-3-8b-slow-DUS-random-method2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |38.52|
+|AI2 Reasoning Challenge (25-Shot)|39.16|
+|HellaSwag (10-Shot)              |63.82|
+|MMLU (5-Shot)                    |30.25|
+|TruthfulQA (0-shot)              |37.04|
+|Winogrande (5-shot)              |60.14|
+|GSM8k (5-shot)                   | 0.68|
+