Adding Evaluation Results

README.md

@@ -1,14 +1,4 @@
 ---
-license: apache-2.0
-datasets:
-- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
-- anthracite-org/stheno-filtered-v1.1
-- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
-- Gryphe/Sonnet3.5-Charcard-Roleplay
-- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
-- anthracite-org/kalo-opus-instruct-22k-no-refusal
-- anthracite-org/nopm_claude_writing_fixed
-- anthracite-org/kalo_opus_misc_240827
 language:
 - en
 - fr
@@ -19,9 +9,114 @@ language:
 - ru
 - zh
 - ja
-pipeline_tag: text-generation
+license: apache-2.0
 tags:
 - merge
+datasets:
+- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
+- anthracite-org/stheno-filtered-v1.1
+- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
+- Gryphe/Sonnet3.5-Charcard-Roleplay
+- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
+- anthracite-org/kalo-opus-instruct-22k-no-refusal
+- anthracite-org/nopm_claude_writing_fixed
+- anthracite-org/kalo_opus_misc_240827
+pipeline_tag: text-generation
+model-index:
+- name: Violet_Twilight-v0.2
+  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: 45.32
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      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: 23.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      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: 2.72
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      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: 2.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      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: 13.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      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: 23.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64adfd277b5ff762771e4571/P962FQhRG4I8nbU_DJolY.png)
@@ -71,4 +166,17 @@ parameters:
     - value: 0.5 # fallback for rest of tensors
 dtype: bfloat16
 
-```
+```
+# [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_Epiculous__Violet_Twilight-v0.2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.53|
+|IFEval (0-Shot)    |45.32|
+|BBH (3-Shot)       |23.94|
+|MATH Lvl 5 (4-Shot)| 2.72|
+|GPQA (0-shot)      | 2.13|
+|MuSR (0-shot)      |13.61|
+|MMLU-PRO (5-shot)  |23.45|
+