Adding Evaluation Results (#12)

- Adding Evaluation Results (610e7bd4cf627f2fb69927b81e80a8cf108eba61)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,15 +1,118 @@
 ---
+language:
+- en
 license: cc-by-sa-4.0
+tags:
+- causal-lm
 datasets:
 - tiiuae/falcon-refinedweb
 - togethercomputer/RedPajama-Data-1T
 - CarperAI/pilev2-dev
 - bigcode/starcoderdata
 - allenai/peS2o
-language:
-- en
-tags:
-- causal-lm
+model-index:
+- name: stablelm-3b-4e1t
+  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: 46.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-3b-4e1t
+      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: 75.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-3b-4e1t
+      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: 45.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-3b-4e1t
+      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: 37.2
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-3b-4e1t
+      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: 71.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-3b-4e1t
+      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: 3.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-3b-4e1t
+      name: Open LLM Leaderboard
 ---
 # `StableLM-3B-4E1T`
 
@@ -128,3 +231,17 @@ As a base model, this model may exhibit unreliable, unsafe, or other undesirable
       author={Tow, Jonathan and Bellagente, Marco and Mahan, Dakota and Riquelme, Carlos}
 }
 ```
+
+# [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-3b-4e1t)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |46.58|
+|AI2 Reasoning Challenge (25-Shot)|46.59|
+|HellaSwag (10-Shot)              |75.94|
+|MMLU (5-Shot)                    |45.23|
+|TruthfulQA (0-shot)              |37.20|
+|Winogrande (5-shot)              |71.19|
+|GSM8k (5-shot)                   | 3.34|
+