Adding Evaluation Results

README.md

@@ -10,6 +10,109 @@ datasets:
 license_name: hsul
 license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md
 pipeline_tag: text-generation
+model-index:
+- name: vortex-3b-v2
+  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: 39.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
+      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: 65.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
+      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: 25.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
+      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: 33.8
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
+      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: 59.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
+      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: 2.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
+      name: Open LLM Leaderboard
 ---
 ![Vortex 3b](https://cdn-lfs-us-1.huggingface.co/repos/68/cb/68cb18839210e9d774c72c739ef72fb95cb03f6f857e6b5a2377406f2078e65a/04b4c8104a551ec9754fd1169842ee67c06ced0fb16569b5fca804c2068578e9?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27vortex%25203b.png%3B+filename%3D%22vortex+3b.png%22%3B&response-content-type=image%2Fpng&Expires=1711282309&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxMTI4MjMwOX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzY4L2NiLzY4Y2IxODgzOTIxMGU5ZDc3NGM3MmM3MzllZjcyZmI5NWNiMDNmNmY4NTdlNmI1YTIzNzc0MDZmMjA3OGU2NWEvMDRiNGM4MTA0YTU1MWVjOTc1NGZkMTE2OTg0MmVlNjdjMDZjZWQwZmIxNjU2OWI1ZmNhODA0YzIwNjg1NzhlOT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=T0d7vhvs9DjdMClzOOEyJMVe4e33u7A-9VTvApC3lMQgW7GXt-hOACXDWDp2TQMv6WoxL7DmGBh-d2uXvGT-2Sqx%7EUcce2pxq1yqtkMEi7sf2WYSHtmaXrIWAiVF%7EPeidG1wRr8wfUY3qIjlKtMVJs7RGbzvAgyvhscazuqutIj37tlIjEcYUXYOuYZoqA3OhoXfpiawCvmXc%7EAul-bAWwAYx91BWvGw9fw4tv20wisJDsh6BV7HEWnV%7EYbXvCxxlZZ4BbcWrYDN%7EMRf48EElCacf5KMpDMbCa52rO-ZvXCWgap%7EzUaIemRSQ84rpgTlVKb--D3GL3pUwRroaiRF7A__&Key-Pair-Id=KCD77M1F0VK2B)
 **Model Overview**
@@ -37,4 +140,16 @@ text = pipeline(model="OEvortex/vortex-3b-v2", torch_dtype=torch.bfloat16, devic
 
 res = text("Explain to me the difference between nuclear fission and fusion.")
 print(res[0]["text"])
-```
+```
+# [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_OEvortex__vortex-3b-v2)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.46|
+|AI2 Reasoning Challenge (25-Shot)|39.68|
+|HellaSwag (10-Shot)              |65.04|
+|MMLU (5-Shot)                    |25.09|
+|TruthfulQA (0-shot)              |33.80|
+|Winogrande (5-shot)              |59.12|
+|GSM8k (5-shot)                   | 2.05|
+