Adding Evaluation Results

README.md

@@ -1,7 +1,110 @@
 ---
-license: apache-2.0
 language:
-  - en
+- en
+license: apache-2.0
+model-index:
+- name: luxia-21.4b-alignment-v1.0
+  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: 77.47
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 91.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 68.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 79.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 87.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 62.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      name: Open LLM Leaderboard
 ---
 
 # **Introduction**
@@ -39,4 +142,17 @@ model = AutoModelForCausalLM.from_pretrained(
 
 
 ### **Contact Us** ###
-Any questions and suggestions are welcomed at the discussion tab.
+Any questions and suggestions are welcomed at the discussion tab.
+# [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_saltlux__luxia-21.4b-alignment-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |77.74|
+|AI2 Reasoning Challenge (25-Shot)|77.47|
+|HellaSwag (10-Shot)              |91.88|
+|MMLU (5-Shot)                    |68.10|
+|TruthfulQA (0-shot)              |79.17|
+|Winogrande (5-shot)              |87.45|
+|GSM8k (5-shot)                   |62.40|
+