Adding Evaluation Results

README.md

@@ -1,22 +1,122 @@
 ---
-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: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 16.52
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 5.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.3
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.09
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 1.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=togethercomputer/RedPajama-INCITE-Chat-3B-v1
+      name: Open LLM Leaderboard
 ---
 
 # RedPajama-INCITE-Chat-3B-v1
@@ -208,4 +308,17 @@ 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/open-llm-leaderboard/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.               | 4.75|
+|IFEval (0-Shot)    |16.52|
+|BBH (3-Shot)       | 5.16|
+|MATH Lvl 5 (4-Shot)| 0.30|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 5.09|
+|MMLU-PRO (5-shot)  | 1.41|
+