Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- NousResearch/Hermes-3-Llama-3.1-8B
-- DavidAU/L3.1-RP-Hero-BigTalker-8B
-- arcee-ai/Llama-3.1-SuperNova-Lite
+license: llama3.1
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.1
+base_model:
+- NousResearch/Hermes-3-Llama-3.1-8B
+- DavidAU/L3.1-RP-Hero-BigTalker-8B
+- arcee-ai/Llama-3.1-SuperNova-Lite
+model-index:
+- name: BigTalker-Lite-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: 36.89
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/BigTalker-Lite-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: 32.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/BigTalker-Lite-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: 9.97
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/BigTalker-Lite-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: 8.05
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/BigTalker-Lite-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: 11.04
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/BigTalker-Lite-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: 27.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/BigTalker-Lite-8B
+      name: Open LLM Leaderboard
 ---
 # merge
 ---
@@ -51,4 +146,17 @@ parameters:
   normalize: false
   int8_mask: true
 dtype: float16
-```
+```
+# [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/Triangle104__BigTalker-Lite-8B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.94|
+|IFEval (0-Shot)    |36.89|
+|BBH (3-Shot)       |32.68|
+|MATH Lvl 5 (4-Shot)| 9.97|
+|GPQA (0-shot)      | 8.05|
+|MuSR (0-shot)      |11.04|
+|MMLU-PRO (5-shot)  |27.01|
+