Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - gsm8k
-language:
-- en
+model-index:
+- name: Marcoroni-neural-chat-7B-v2_gsm8k_merged
+  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: 65.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fzzhang/Marcoroni-neural-chat-7B-v2_gsm8k_merged
+      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: 85.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fzzhang/Marcoroni-neural-chat-7B-v2_gsm8k_merged
+      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: 64.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fzzhang/Marcoroni-neural-chat-7B-v2_gsm8k_merged
+      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: 53.18
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fzzhang/Marcoroni-neural-chat-7B-v2_gsm8k_merged
+      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: 78.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fzzhang/Marcoroni-neural-chat-7B-v2_gsm8k_merged
+      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: 61.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fzzhang/Marcoroni-neural-chat-7B-v2_gsm8k_merged
+      name: Open LLM Leaderboard
 ---
 # Marcoroni-neural-chat-7B-v2_gsm8k
 
@@ -44,4 +147,17 @@ The following hyperparameters were used during training:
 - Transformers 4.36.2
 - Pytorch 2.1.2
 - Datasets 2.16.1
-- Tokenizers 0.15.1
+- Tokenizers 0.15.1
+# [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_fzzhang__Marcoroni-neural-chat-7B-v2_gsm8k_merged)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.13|
+|AI2 Reasoning Challenge (25-Shot)|65.78|
+|HellaSwag (10-Shot)              |85.26|
+|MMLU (5-Shot)                    |64.26|
+|TruthfulQA (0-shot)              |53.18|
+|Winogrande (5-shot)              |78.93|
+|GSM8k (5-shot)                   |61.33|
+