Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - cerebras/SlimPajama-627B
 - bigcode/starcoderdata
 - OpenAssistant/oasst_top1_2023-08-25
-language:
-- en
+model-index:
+- name: TinyLlama-1.1B-Chat-v0.5
+  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: 16.34
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.5
+      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: 3.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.5
+      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: 0.08
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.5
+      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-v0.5
+      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: 3.57
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.5
+      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: 1.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.5
+      name: Open LLM Leaderboard
 ---
 <div align="center">
 
@@ -59,4 +154,17 @@ sequences = pipeline(
 
 for seq in sequences:
     print(f"Result: {seq['generated_text']}")
-```
+```
+# [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-v0.5)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 4.08|
+|IFEval (0-Shot)    |16.34|
+|BBH (3-Shot)       | 3.41|
+|MATH Lvl 5 (4-Shot)| 0.08|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 3.57|
+|MMLU-PRO (5-shot)  | 1.07|
+