Adding Evaluation Results

README.md

@@ -10,8 +10,103 @@ base_model:
 - cognitivecomputations/dolphin-2.9.4-llama3.1-8b
 - NousResearch/Hermes-3-Llama-3.1-8B
 - NeverSleep/Lumimaid-v0.2-8B
-- Sao10K/L3-8B-Stheno-v3.2 
+- Sao10K/L3-8B-Stheno-v3.2
 - DreadPoor/ScaduTorrent-8B-model_stock
+model-index:
+- name: Trinas_Nectar-8B-model_stock
+  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: 72.59
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Trinas_Nectar-8B-model_stock
+      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: 31.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Trinas_Nectar-8B-model_stock
+      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: 13.75
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Trinas_Nectar-8B-model_stock
+      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: 4.81
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Trinas_Nectar-8B-model_stock
+      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: 11.41
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Trinas_Nectar-8B-model_stock
+      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: 29.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Trinas_Nectar-8B-model_stock
+      name: Open LLM Leaderboard
 ---
 
 # Trinas_Nectar-8B-model_stock
@@ -34,4 +129,17 @@ base_model: Sao10K/L3-8B-Stheno-v3.2
 normalize: false
 int8_mask: true
 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_DreadPoor__Trinas_Nectar-8B-model_stock)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.27|
+|IFEval (0-Shot)    |72.59|
+|BBH (3-Shot)       |31.98|
+|MATH Lvl 5 (4-Shot)|13.75|
+|GPQA (0-shot)      | 4.81|
+|MuSR (0-shot)      |11.41|
+|MMLU-PRO (5-shot)  |29.09|
+