Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 datasets:
 - togethercomputer/RedPajama-Data-1T
 - databricks/databricks-dolly-15k
 - OpenAssistant/oasst1
 - Muennighoff/natural-instructions
 - Muennighoff/P3
-language:
-- en
 pipeline_tag: text-generation
-library_name: transformers
+model-index:
+- name: RedPajama-INCITE-Chat-Instruct-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: 42.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-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: 67.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-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: 25.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-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: 33.62
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-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: 64.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-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: 0.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+      name: Open LLM Leaderboard
 ---
 
 <a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
@@ -34,3 +137,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | TruthfulQA (0-shot)   | 33.62   |
 | Winogrande (5-shot)   | 64.8   |
 | GSM8K (5-shot)        | 0.91        |
+
+# [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_acrastt__RedPajama-INCITE-Chat-Instruct-3B-V1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |39.23|
+|AI2 Reasoning Challenge (25-Shot)|42.58|
+|HellaSwag (10-Shot)              |67.48|
+|MMLU (5-Shot)                    |25.99|
+|TruthfulQA (0-shot)              |33.62|
+|Winogrande (5-shot)              |64.80|
+|GSM8k (5-shot)                   | 0.91|
+