Adding Evaluation Results

README.md

@@ -1,19 +1,123 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - cerebras/SlimPajama-627B
 - bigcode/starcoderdata
 - HuggingFaceH4/ultrachat_200k
 - HuggingFaceH4/ultrafeedback_binarized
-language:
-- en
 widget:
-  - example_title: Fibonacci (Python)
-    messages:
-    - role: system
-      content: You are a chatbot who can help code!
-    - role: user
-      content: Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.
+- example_title: Fibonacci (Python)
+  messages:
+  - role: system
+    content: You are a chatbot who can help code!
+  - role: user
+    content: Write me a function to calculate the first 10 digits of the fibonacci
+      sequence in Python and print it out to the CLI.
+model-index:
+- name: TinyLlama-1.1B-Chat-v1.0
+  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: 36.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      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: 61.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      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: 25.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      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: 37.48
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      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: 61.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      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: 2.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      name: Open LLM Leaderboard
 ---
 <div align="center">
 
@@ -63,4 +167,17 @@ print(outputs[0]["generated_text"])
 # How many helicopters can a human eat in one sitting?</s>
 # <|assistant|>
 # ...
-```
+```
+# [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_TinyLlama__TinyLlama-1.1B-Chat-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.28|
+|AI2 Reasoning Challenge (25-Shot)|36.09|
+|HellaSwag (10-Shot)              |61.10|
+|MMLU (5-Shot)                    |25.39|
+|TruthfulQA (0-shot)              |37.48|
+|Winogrande (5-shot)              |61.25|
+|GSM8k (5-shot)                   | 2.35|
+