Adding Evaluation Results

README.md

@@ -1,16 +1,111 @@
 ---
-base_model:
-- GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
-- aisingapore/gemma2-9b-cpt-sea-lionv3-instruct
-tags:
-- merge
-- mergekit
-license: gemma
 language:
 - en
 - id
 - jv
 - su
+license: gemma
+tags:
+- merge
+- mergekit
+base_model:
+- GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
+- aisingapore/gemma2-9b-cpt-sea-lionv3-instruct
+model-index:
+- name: gemma2-9b-sahabatai-v1-instruct-BaseTIES
+  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: 73.78
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES
+      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: 43.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES
+      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: 19.34
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES
+      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: 9.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES
+      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: 19.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES
+      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: 37.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES
+      name: Open LLM Leaderboard
 ---
 
 # SahabatAI-Lion-9B-TIES-v1
@@ -69,4 +164,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_gmonsoon__gemma2-9b-sahabatai-v1-instruct-BaseTIES)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |33.70|
+|IFEval (0-Shot)    |73.78|
+|BBH (3-Shot)       |43.40|
+|MATH Lvl 5 (4-Shot)|19.34|
+|GPQA (0-shot)      | 9.40|
+|MuSR (0-shot)      |19.13|
+|MMLU-PRO (5-shot)  |37.19|
+