Adding Evaluation Results

README.md

@@ -1,19 +1,115 @@
 ---
+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: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 5.96
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 4.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 4.31
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/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-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 1.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v1.0
+      name: Open LLM Leaderboard
 ---
 <div align="center">
 
@@ -63,4 +159,17 @@ 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/open-llm-leaderboard/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.               | 2.71|
+|IFEval (0-Shot)    | 5.96|
+|BBH (3-Shot)       | 4.01|
+|MATH Lvl 5 (4-Shot)| 0.83|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 4.31|
+|MMLU-PRO (5-shot)  | 1.12|
+