Adding Evaluation Results

README.md

@@ -1,23 +1,125 @@
 ---
-license: cc-by-nc-4.0
 language:
 - en
+license: cc-by-nc-4.0
 pipeline_tag: text-generation
 widget:
-  - text: >-
-      Below is an instruction that describes a task.
-      
-      Write a response that appropriately completes the request.
-
-      
-      
-      ### Instruction:
-      
-      how can I become more healthy?
-      
-      
-      ### Response:
-    example_title: example
+- text: 'Below is an instruction that describes a task.
+
+    Write a response that appropriately completes the request.
+
+
+
+    ### Instruction:
+
+    how can I become more healthy?
+
+
+    ### Response:'
+  example_title: example
+model-index:
+- name: lamini-neo-1.3b
+  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: 32.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MBZUAI/lamini-neo-1.3b
+      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: 49.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MBZUAI/lamini-neo-1.3b
+      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: 28.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MBZUAI/lamini-neo-1.3b
+      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: 41.05
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MBZUAI/lamini-neo-1.3b
+      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: 56.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MBZUAI/lamini-neo-1.3b
+      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: 0.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MBZUAI/lamini-neo-1.3b
+      name: Open LLM Leaderboard
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -156,4 +258,17 @@ More information needed
   eprinttype   = {arXiv},
   eprint       = {2304.14402}
 }
-```
+```
+# [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_MBZUAI__lamini-neo-1.3b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |34.73|
+|AI2 Reasoning Challenge (25-Shot)|32.76|
+|HellaSwag (10-Shot)              |49.13|
+|MMLU (5-Shot)                    |28.79|
+|TruthfulQA (0-shot)              |41.05|
+|Winogrande (5-shot)              |56.51|
+|GSM8k (5-shot)                   | 0.15|
+