Adding Evaluation Results

README.md

@@ -1,12 +1,4 @@
 ---
-license: other
-datasets:
-- tiiuae/falcon-refinedweb
-- togethercomputer/RedPajama-Data-1T
-- uonlp/CulturaX
-- CarperAI/pilev2-dev
-- bigcode/starcoderdata
-- DataProvenanceInitiative/Commercially-Verified-Licenses
 language:
 - en
 - de
@@ -15,8 +7,119 @@ language:
 - it
 - nl
 - pt
+license: other
 tags:
 - causal-lm
+datasets:
+- tiiuae/falcon-refinedweb
+- togethercomputer/RedPajama-Data-1T
+- uonlp/CulturaX
+- CarperAI/pilev2-dev
+- bigcode/starcoderdata
+- DataProvenanceInitiative/Commercially-Verified-Licenses
+model-index:
+- name: stablelm-2-1_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: 43.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-1_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: 70.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-1_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: 38.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-1_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: 36.78
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-1_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: 64.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-1_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: 17.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-1_6b
+      name: Open LLM Leaderboard
 ---
 # `Stable LM 2 1.6B`
 
@@ -135,3 +238,17 @@ As a base model, this model may exhibit unreliable, unsafe, or other undesirable
       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-2-1_6b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |45.25|
+|AI2 Reasoning Challenge (25-Shot)|43.34|
+|HellaSwag (10-Shot)              |70.45|
+|MMLU (5-Shot)                    |38.95|
+|TruthfulQA (0-shot)              |36.78|
+|Winogrande (5-shot)              |64.56|
+|GSM8k (5-shot)                   |17.44|
+