Adding Evaluation Results

README.md

@@ -1,14 +1,128 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - cerebras/SlimPajama-627B
 - bigcode/starcoderdata
 - HuggingFaceH4/ultrachat_200k
 - HuggingFaceH4/ultrafeedback_binarized
-language:
-- en
 widget:
-- text: "<|system|>\nYou are a chatbot who can help code!</s>\n<|user|>\nWrite out the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.</s>\n<|assistant|>\n"
+- text: '<|system|>
+
+    You are a chatbot who can help code!</s>
+
+    <|user|>
+
+    Write out the first 10 digits of the fibonacci sequence in Python and print it
+    out to the CLI.</s>
+
+    <|assistant|>
+
+    '
+model-index:
+- name: TinyLlama-repeat
+  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: 35.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Deathsquad10/TinyLlama-repeat
+      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: 60.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Deathsquad10/TinyLlama-repeat
+      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: 26.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Deathsquad10/TinyLlama-repeat
+      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: 38.78
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Deathsquad10/TinyLlama-repeat
+      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: 60.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Deathsquad10/TinyLlama-repeat
+      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: 1.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Deathsquad10/TinyLlama-repeat
+      name: Open LLM Leaderboard
 ---
 <div align="center">
 
@@ -71,4 +185,17 @@ 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_Deathsquad10__TinyLlama-repeat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.09|
+|AI2 Reasoning Challenge (25-Shot)|35.24|
+|HellaSwag (10-Shot)              |60.25|
+|MMLU (5-Shot)                    |26.07|
+|TruthfulQA (0-shot)              |38.78|
+|Winogrande (5-shot)              |60.46|
+|GSM8k (5-shot)                   | 1.74|
+