Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 datasets:
 - togethercomputer/RedPajama-Data-1T
+model-index:
+- name: RedPajama-INCITE-Base-7B-v0.1
+  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: 46.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Base-7B-v0.1
+      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: 71.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Base-7B-v0.1
+      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: 27.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Base-7B-v0.1
+      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: 33.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Base-7B-v0.1
+      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: 67.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Base-7B-v0.1
+      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: 1.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Base-7B-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # RedPajama-INCITE-7B-Base
@@ -210,4 +313,17 @@ The checkpoints are organized based on the number of tokens they contain, rangin
 
 ## Community
 
-Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
+Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
+# [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_togethercomputer__RedPajama-INCITE-Base-7B-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |41.25|
+|AI2 Reasoning Challenge (25-Shot)|46.25|
+|HellaSwag (10-Shot)              |71.63|
+|MMLU (5-Shot)                    |27.68|
+|TruthfulQA (0-shot)              |33.03|
+|Winogrande (5-shot)              |67.32|
+|GSM8k (5-shot)                   | 1.59|
+