Adding Evaluation Results

README.md

@@ -9,9 +9,104 @@ tags:
 - llama
 - trl
 base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
-pipeline_tag: text-generation
 datasets:
 - LimYeri/LeetCode_Python_Solutions
+pipeline_tag: text-generation
+model-index:
+- name: CodeMind-Llama3-8B-unsloth_v2-merged
+  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: 69.46
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LimYeri/CodeMind-Llama3-8B-unsloth_v2-merged
+      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: 26.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LimYeri/CodeMind-Llama3-8B-unsloth_v2-merged
+      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: 5.74
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LimYeri/CodeMind-Llama3-8B-unsloth_v2-merged
+      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: 2.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LimYeri/CodeMind-Llama3-8B-unsloth_v2-merged
+      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: 2.22
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LimYeri/CodeMind-Llama3-8B-unsloth_v2-merged
+      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: 27.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LimYeri/CodeMind-Llama3-8B-unsloth_v2-merged
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -38,4 +133,17 @@ The following hyperparameters are used during SFT:
 - lora_dropout: 0
 - gradient_checkpointing: true
 - fp16: not is_bfloat16_supported()
-- bf16: is_bfloat16_supported()
+- bf16: is_bfloat16_supported()
+# [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_LimYeri__CodeMind-Llama3-8B-unsloth_v2-merged)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.32|
+|IFEval (0-Shot)    |69.46|
+|BBH (3-Shot)       |26.66|
+|MATH Lvl 5 (4-Shot)| 5.74|
+|GPQA (0-shot)      | 2.01|
+|MuSR (0-shot)      | 2.22|
+|MMLU-PRO (5-shot)  |27.84|
+