Adding Evaluation Results

README.md

@@ -1,4 +1,9 @@
 ---
+language:
+- en
+license: other
+tags:
+- causal-lm
 datasets:
 - HuggingFaceH4/ultrachat_200k
 - allenai/ultrafeedback_binarized_cleaned
@@ -8,17 +13,107 @@ datasets:
 - LDJnr/Capybara
 - Intel/orca_dpo_pairs
 - hkust-nlp/deita-10k-v0
-language:
-- en
-tags:
-- causal-lm
 extra_gated_fields:
   Name: text
   Email: text
   Country: text
   Organization or Affiliation: text
   I ALLOW Stability AI to email me about new model releases: checkbox
-license: other
+model-index:
+- name: stablelm-2-zephyr-1_6b
+  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: 32.79
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 6.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 2.11
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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=stabilityai/stablelm-2-zephyr-1_6b
+      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: 5.99
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 7.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      name: Open LLM Leaderboard
 ---
 # `StableLM 2 Zephyr 1.6B`
 
@@ -155,4 +250,17 @@ Finally, do not use the models if they are unsuitable for your application, or f
       title={Stable LM 2 1.6B},
       author={Stability AI Language Team}
 }
-```
+```
+# [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_stabilityai__stablelm-2-zephyr-1_6b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 9.50|
+|IFEval (0-Shot)    |32.79|
+|BBH (3-Shot)       | 6.71|
+|MATH Lvl 5 (4-Shot)| 2.11|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 5.99|
+|MMLU-PRO (5-shot)  | 7.93|
+