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 +13,115 @@ 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: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 43.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 69.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 42.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 45.11
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 64.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      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: 35.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
+      name: Open LLM Leaderboard
 ---
 # `StableLM 2 Zephyr 1.6B`
 
@@ -155,4 +258,17 @@ 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/HuggingFaceH4/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.                             |49.99|
+|AI2 Reasoning Challenge (25-Shot)|43.69|
+|HellaSwag (10-Shot)              |69.30|
+|MMLU (5-Shot)                    |42.03|
+|TruthfulQA (0-shot)              |45.11|
+|Winogrande (5-shot)              |64.48|
+|GSM8k (5-shot)                   |35.33|
+