Update README.md

README.md

@@ -74,6 +74,101 @@ language:
 - es
 - en
 pipeline_tag: text-generation
+model-index:
+- name: HarmfulProject-3.2-1B
+  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: 39.22
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
+      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: 9.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
+      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: 7
+    metrics:
+    - type: exact_match
+      value: 7.48
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
+      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: 2.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
+      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: 3.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
+      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: 10.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
+      name: Open LLM Leaderboard
 ---
 
 <center> <img src="https://i.ibb.co/hJk8j3Rz/IMG-20250306-WA0039.jpg" alt="IMG-20250306-WA0039" border="0"></a> </center>
@@ -82,6 +177,20 @@ pipeline_tag: text-generation
 
 <center>   <img src="https://i.ibb.co/35vWL8Lc/IMG-20250311-011611.jpg" alt="IMG-20250311-011611" border="0"></a>  </center>
 
+# [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/Novaciano__BLAST_PROCESSING-3.2-1B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |11.95|
+|IFEval (0-Shot)    |39.22|
+|BBH (3-Shot)       | 9.36|
+|MATH Lvl 5 (4-Shot)| 7.48|
+|GPQA (0-shot)      | 2.13|
+|MuSR (0-shot)      | 3.06|
+|MMLU-PRO (5-shot)  | 10.46|
+
 # Mezcla
 
 Esta mezcla de 20 modelos pre-entrenados fue creado usando [mergekit](https://github.com/cg123/mergekit).