Adding Evaluation Results (#2)

- Adding Evaluation Results (4908576e259efb77e48d4a551fa7cb890060ca0e)


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

README.md

@@ -1,6 +1,7 @@
 ---
-library_name: transformers
 license: other
+library_name: transformers
+base_model: meta-llama/Meta-Llama-3-8B
 datasets:
 - mlabonne/orpo-dpo-mix-40k
 - Open-Orca/SlimOrca-Dedup
@@ -8,7 +9,109 @@ datasets:
 - microsoft/orca-math-word-problems-200k
 - m-a-p/Code-Feedback
 - MaziyarPanahi/WizardLM_evol_instruct_V2_196k
-base_model: meta-llama/Meta-Llama-3-8B
+model-index:
+- name: llama-3-neural-chat-v1-8b
+  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: 60.84
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
+      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: 84.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
+      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: 64.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
+      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: 56.34
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
+      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: 78.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
+      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: 54.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
+      name: Open LLM Leaderboard
 ---
 
 # llama-3-neural-chat-v1-8b
@@ -77,4 +180,17 @@ Conversational AI.
 | - agieval_sat_en_without_passage|      1|none            |     0|acc        |0.4175|±  |0.0344|
 |                                 |       |none            |     0|acc_norm   |0.3738|±  |0.0338|
 | - agieval_sat_math              |      1|none            |     0|acc        |0.4227|±  |0.0334|
-|                                 |       |none            |     0|acc_norm   |0.3682|±  |0.0326|
+|                                 |       |none            |     0|acc_norm   |0.3682|±  |0.0326|
+# [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_Locutusque__llama-3-neural-chat-v1-8b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.50|
+|AI2 Reasoning Challenge (25-Shot)|60.84|
+|HellaSwag (10-Shot)              |84.13|
+|MMLU (5-Shot)                    |64.69|
+|TruthfulQA (0-shot)              |56.34|
+|Winogrande (5-shot)              |78.22|
+|GSM8k (5-shot)                   |54.81|
+