Adding Evaluation Results

README.md

@@ -1,7 +1,102 @@
 ---
-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: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 36.93
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 48.02
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 6.19
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 6.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      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: 12.51
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/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-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 26.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
+      name: Open LLM Leaderboard
 ---
 
 # **Introduction**
@@ -39,4 +134,17 @@ 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/open-llm-leaderboard/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.               |22.86|
+|IFEval (0-Shot)    |36.93|
+|BBH (3-Shot)       |48.02|
+|MATH Lvl 5 (4-Shot)| 6.19|
+|GPQA (0-shot)      | 6.82|
+|MuSR (0-shot)      |12.51|
+|MMLU-PRO (5-shot)  |26.70|
+