Adding Evaluation Results (#1)

- Adding Evaluation Results (db43425f70945ad983b663a3d52d45464327a0f8)


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

README.md

@@ -1,11 +1,106 @@
 ---
-base_model:
-- arcee-ai/Llama-3.1-SuperNova-Lite
 tags:
 - merge
 - mergekit
 - lazymergekit
 - arcee-ai/Llama-3.1-SuperNova-Lite
+base_model:
+- arcee-ai/Llama-3.1-SuperNova-Lite
+model-index:
+- name: 1PARAMMYL-8B-ModelStock
+  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: 53.71
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/1PARAMMYL-8B-ModelStock
+      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: 31.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/1PARAMMYL-8B-ModelStock
+      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: 13.14
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/1PARAMMYL-8B-ModelStock
+      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: 9.84
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/1PARAMMYL-8B-ModelStock
+      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: 14.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/1PARAMMYL-8B-ModelStock
+      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: 33.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/1PARAMMYL-8B-ModelStock
+      name: Open LLM Leaderboard
 ---
 
 # 1PARAMMYL-8B-ModelStock
@@ -52,4 +147,17 @@ 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_Youlln__1PARAMMYL-8B-ModelStock)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.02|
+|IFEval (0-Shot)    |53.71|
+|BBH (3-Shot)       |31.80|
+|MATH Lvl 5 (4-Shot)|13.14|
+|GPQA (0-shot)      | 9.84|
+|MuSR (0-shot)      |14.28|
+|MMLU-PRO (5-shot)  |33.34|
+