Adding Evaluation Results

README.md

@@ -1,5 +1,9 @@
 ---
 license: apache-2.0
+tags:
+- Composer
+- MosaicML
+- llm-foundry
 datasets:
 - competition_math
 - knkarthick/dialogsum
@@ -10,11 +14,110 @@ datasets:
 - spider
 - gsm8k
 - allenai/qasper
-tags:
-- Composer
-- MosaicML
-- llm-foundry
 inference: false
+model-index:
+- name: mpt-30b-instruct
+  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: 58.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-30b-instruct
+      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: 84.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-30b-instruct
+      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: 49.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-30b-instruct
+      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: 38.05
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-30b-instruct
+      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: 75.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-30b-instruct
+      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: 15.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-30b-instruct
+      name: Open LLM Leaderboard
 ---
 
 # MPT-30B-Instruct
@@ -232,4 +335,17 @@ for open-source foundation models},
     note      = {Accessed: 2023-06-22},
     urldate   = {2023-06-22}
 }
-```
+```
+# [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_mosaicml__mpt-30b-instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |53.40|
+|AI2 Reasoning Challenge (25-Shot)|58.45|
+|HellaSwag (10-Shot)              |84.31|
+|MMLU (5-Shot)                    |49.15|
+|TruthfulQA (0-shot)              |38.05|
+|Winogrande (5-shot)              |75.14|
+|GSM8k (5-shot)                   |15.31|
+