Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-base_model: HuggingFaceTB/SmolLM-1.7B-Instruct
-datasets: gabrielmbmb/ifeval-trl
 library_name: transformers
-model_name: SmolLM-1.7B-Instruct-IFEval
 tags:
 - generated_from_trainer
 - trl
 - sft
+base_model: HuggingFaceTB/SmolLM-1.7B-Instruct
+datasets: gabrielmbmb/ifeval-trl
+model_name: SmolLM-1.7B-Instruct-IFEval
 licence: license
+model-index:
+- name: SmolLM-1.7B-Instruct-IFEval
+  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: 23.06
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gabrielmbmb/SmolLM-1.7B-Instruct-IFEval
+      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: 4.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gabrielmbmb/SmolLM-1.7B-Instruct-IFEval
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gabrielmbmb/SmolLM-1.7B-Instruct-IFEval
+      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: 0.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gabrielmbmb/SmolLM-1.7B-Instruct-IFEval
+      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: 1.6
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gabrielmbmb/SmolLM-1.7B-Instruct-IFEval
+      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: 1.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=gabrielmbmb/SmolLM-1.7B-Instruct-IFEval
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for SmolLM-1.7B-Instruct-IFEval
@@ -55,4 +150,17 @@ Cite TRL as:
 	publisher    = {GitHub},
 	howpublished = {\url{https://github.com/huggingface/trl}}
 }
-```
+```
+# [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_gabrielmbmb__SmolLM-1.7B-Instruct-IFEval)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 5.22|
+|IFEval (0-Shot)    |23.06|
+|BBH (3-Shot)       | 4.50|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 0.45|
+|MuSR (0-shot)      | 1.60|
+|MMLU-PRO (5-shot)  | 1.73|
+