Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,22 +1,130 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 datasets:
 - togethercomputer/RedPajama-Data-1T
 - OpenAssistant/oasst1
 - databricks/databricks-dolly-15k
 widget:
-- text: "<human>: Write an email to my friends inviting them to come to my home on Friday for a dinner party, bring their own food to share.\n<bot>:"
-  example_title: "Email Writing"
-- text: "<human>: Create a list of things to do in San Francisco\n<bot>:"
-  example_title: "Brainstorming"
+- text: '<human>: Write an email to my friends inviting them to come to my home on
+    Friday for a dinner party, bring their own food to share.
+
+    <bot>:'
+  example_title: Email Writing
+- text: '<human>: Create a list of things to do in San Francisco
+
+    <bot>:'
+  example_title: Brainstorming
 inference:
   parameters:
     temperature: 0.7
     top_p: 0.7
     top_k: 50
     max_new_tokens: 128
+model-index:
+- name: RedPajama-INCITE-Chat-3B-v1
+  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: 42.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      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: 67.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      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: 26.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      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: 34.44
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      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: 65.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      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: 0.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      name: Open LLM Leaderboard
 ---
 
 # RedPajama-INCITE-Chat-3B-v1
@@ -208,4 +316,17 @@ Please refer to [togethercomputer/RedPajama-Data-1T](https://huggingface.co/data
 
 ## 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-Chat-3B-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |39.53|
+|AI2 Reasoning Challenge (25-Shot)|42.83|
+|HellaSwag (10-Shot)              |67.62|
+|MMLU (5-Shot)                    |26.23|
+|TruthfulQA (0-shot)              |34.44|
+|Winogrande (5-shot)              |65.51|
+|GSM8k (5-shot)                   | 0.53|
+