Adding Evaluation Results

README.md

@@ -1,15 +1,121 @@
 ---
+license: mit
 library_name: transformers
 base_model: Josephgflowers/TinyLlama-3T-Cinder-v1.2
-license: mit
 pipeline_tag: text-generation
 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|>'
+model-index:
+- name: Cinder-1.3B-Test
+  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: 33.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/Cinder-1.3B-Test
+      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: 55.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/Cinder-1.3B-Test
+      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: 26.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/Cinder-1.3B-Test
+      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: 36.62
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/Cinder-1.3B-Test
+      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: 58.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/Cinder-1.3B-Test
+      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: 2.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Josephgflowers/Cinder-1.3B-Test
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -210,4 +316,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Framework versions
 
-- PEFT 0.7.1
+- PEFT 0.7.1
+# [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_Josephgflowers__Cinder-1.3B-Test)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |35.57|
+|AI2 Reasoning Challenge (25-Shot)|33.19|
+|HellaSwag (10-Shot)              |55.48|
+|MMLU (5-Shot)                    |26.37|
+|TruthfulQA (0-shot)              |36.62|
+|Winogrande (5-shot)              |58.96|
+|GSM8k (5-shot)                   | 2.81|
+