Adding Evaluation Results (#1)

- Adding Evaluation Results (91c9ac6c6533c0afebb4aa7a129dbf78fc0b6c09)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,4 +1,8 @@
 ---
+language:
+- en
+license: llama3
+library_name: transformers
 tags:
 - merge
 - mergekit
@@ -8,11 +12,6 @@ tags:
 - rp
 - roleplay
 - role-play
-license: llama3
-language:
-- en
-library_name: transformers
-pipeline_tag: text-generation
 base_model:
 - Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
 - bluuwhale/L3-SthenoMaidBlackroot-8B-V1
@@ -26,6 +25,102 @@ base_model:
 - aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-32K
 - Nitral-AI/Hathor_Stable-v0.2-L3-8B
 - Sao10K/L3-8B-Stheno-v3.1
+pipeline_tag: text-generation
+model-index:
+- name: L3-Umbral-Mind-RP-v2.0-8B
+  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: 71.23
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
+      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: 32.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
+      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: 10.12
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
+      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: 4.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
+      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: 5.55
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
+      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: 30.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
+      name: Open LLM Leaderboard
 ---
 
 <img src="https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v3-8B/resolve/main/63073798_p0_master1200.jpg" style="display: block; margin: auto;">
@@ -224,4 +319,17 @@ models:
 merge_method: task_arithmetic
 base_model: Casual-Autopsy/Umbral-Mind-3
 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_Casual-Autopsy__L3-Umbral-Mind-RP-v2.0-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.76|
+|IFEval (0-Shot)    |71.23|
+|BBH (3-Shot)       |32.49|
+|MATH Lvl 5 (4-Shot)|10.12|
+|GPQA (0-shot)      | 4.92|
+|MuSR (0-shot)      | 5.55|
+|MMLU-PRO (5-shot)  |30.26|
+