Adding Evaluation Results

README.md

@@ -1,5 +1,7 @@
 ---
-base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.8
+language:
+- en
+license: other
 library_name: transformers
 tags:
 - axolotl
@@ -9,16 +11,117 @@ tags:
 - pytorch
 - llama
 - llama-3
-language:
-- en
+base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.8
+model_name: Llama-3-8B-Instruct-v0.9
 pipeline_tag: text-generation
-license: other
 license_name: llama3
 license_link: LICENSE
 inference: false
 model_creator: MaziyarPanahi
-model_name: Llama-3-8B-Instruct-v0.9
 quantized_by: MaziyarPanahi
+model-index:
+- name: Llama-3-8B-Instruct-v0.9
+  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: 72.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 88.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 68.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 64.67
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 79.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 66.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      name: Open LLM Leaderboard
 ---
 
 <img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -114,3 +217,17 @@ outputs = pipeline(
 )
 print(outputs[0]["generated_text"][len(prompt):])
 ```
+
+# [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_MaziyarPanahi__Llama-3-8B-Instruct-v0.9)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.29|
+|AI2 Reasoning Challenge (25-Shot)|72.35|
+|HellaSwag (10-Shot)              |88.17|
+|MMLU (5-Shot)                    |68.10|
+|TruthfulQA (0-shot)              |64.67|
+|Winogrande (5-shot)              |79.95|
+|GSM8k (5-shot)                   |66.49|
+