Adding Evaluation Results (#1)

- Adding Evaluation Results (3e617523c6eba47472a65be6511eb6bf22826656)


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

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code
 language:
 - en
 license: apache-2.0
@@ -9,8 +8,104 @@ tags:
 - unsloth
 - llama
 - trl
+base_model: EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code
 datasets:
 - EpistemeAI/agentic-test1
+model-index:
+- name: Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math
+  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: 55.15
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math
+      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: 26.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math
+      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: 12.01
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math
+      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: 7.27
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math
+      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: 6.79
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math
+      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: 26.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math
+      name: Open LLM Leaderboard
 ---
 
 # Agent LLama
@@ -237,4 +332,17 @@ Go to model card [Llama-Guard](https://huggingface.co/meta-llama/Llama-Guard-3-8
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+# [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_EpistemeAI2__Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-math)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.48|
+|IFEval (0-Shot)    |55.15|
+|BBH (3-Shot)       |26.74|
+|MATH Lvl 5 (4-Shot)|12.01|
+|GPQA (0-shot)      | 7.27|
+|MuSR (0-shot)      | 6.79|
+|MMLU-PRO (5-shot)  |26.89|
+