Adding Evaluation Results (#2)

- Adding Evaluation Results (8e39130a3032a02cf2134325396a2eed54dd9fc3)

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: unsloth/Llama-3.2-1B-Instruct-bnb-4bit
 language:
 - en
 license: llama3.2
@@ -11,8 +10,104 @@ tags:
 - llama-3
 - trl
 - sft
+base_model: unsloth/Llama-3.2-1B-Instruct-bnb-4bit
 datasets:
 - mlabonne/FineTome-100k
+model-index:
+- name: FineTome-Llama3.2-1B-0929
+  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: 39.91
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-Llama3.2-1B-0929
+      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: 5.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-Llama3.2-1B-0929
+      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: 1.28
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-Llama3.2-1B-0929
+      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: 3.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-Llama3.2-1B-0929
+      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: 2.66
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-Llama3.2-1B-0929
+      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: 4.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-Llama3.2-1B-0929
+      name: Open LLM Leaderboard
 ---
 
 # Notice
@@ -139,4 +234,17 @@ Who are you? Briefy introduce yourself.
 **Output**:
 ```
 Hi there! I'm an AI assistant designed to help with a range of inquiries. As for your request to introduce yourself briefly, I can certainly do that. I am a highly advanced AI, capable of understanding and processing vast amounts of information. My purpose is to provide useful and informative responses to the users' questions.<|eot_id|>
-```
+```
+# [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_NotASI__FineTome-Llama3.2-1B-0929)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 9.56|
+|IFEval (0-Shot)    |39.91|
+|BBH (3-Shot)       | 5.74|
+|MATH Lvl 5 (4-Shot)| 1.28|
+|GPQA (0-shot)      | 3.02|
+|MuSR (0-shot)      | 2.66|
+|MMLU-PRO (5-shot)  | 4.76|
+