Adding Evaluation Results

README.md

@@ -1,30 +1,132 @@
 ---
 license: mit
 widget:
-  - text: >
-      <|system|>
-      
-      You are a helpful assistant</s>
-      
-      <|user|>
-      
-      Tell me about yourself, what is your name?.</s>
-      
-      <|assistant|>
+- text: '<|system|>
 
+    You are a helpful assistant</s>
+
+    <|user|>
+
+    Tell me about yourself, what is your name?.</s>
+
+    <|assistant|>
+
+    '
 widget2:
-  - text: >
-      <|system|>
-      
-      You are a helpful assistant</s>
-      
-      <|user|>
-      
-      How about another amazing adventure on The Cinder Show!</s>
-      
-      <|assistant|>
-
-      
+- text: '<|system|>
+
+    You are a helpful assistant</s>
+
+    <|user|>
+
+    How about another amazing adventure on The Cinder Show!</s>
+
+    <|assistant|>
+
+    '
+model-index:
+- name: TinyLlama-3T-Cinder-v1.1
+  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: 34.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/TinyLlama-3T-Cinder-v1.1
+      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: 50.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/TinyLlama-3T-Cinder-v1.1
+      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: 25.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/TinyLlama-3T-Cinder-v1.1
+      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: 37.57
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/TinyLlama-3T-Cinder-v1.1
+      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: 56.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/TinyLlama-3T-Cinder-v1.1
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/TinyLlama-3T-Cinder-v1.1
+      name: Open LLM Leaderboard
 ---
 Model Card for Cinder
 Model Name: Cinder
@@ -74,3 +176,17 @@ I encourage collaboration and contributions to expand Cinder's educational and c
 If you have any suggestions or requests please leave them in the newly created discord channel.
 https://discord.gg/5ebjDrnZ
 
+
+# [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_Josephgflowers__TinyLlama-3T-Cinder-v1.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |34.03|
+|AI2 Reasoning Challenge (25-Shot)|34.04|
+|HellaSwag (10-Shot)              |50.40|
+|MMLU (5-Shot)                    |25.75|
+|TruthfulQA (0-shot)              |37.57|
+|Winogrande (5-shot)              |56.43|
+|GSM8k (5-shot)                   | 0.00|
+