Adding Evaluation Results

README.md

@@ -1,9 +1,104 @@
 ---
 language:
 - en
+license: apache-2.0
 library_name: transformers
 pipeline_tag: text-generation
-license: apache-2.0
+model-index:
+- name: speechless-zephyr-code-functionary-7b
+  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: 26.96
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=uukuguy/speechless-zephyr-code-functionary-7b
+      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: 25.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=uukuguy/speechless-zephyr-code-functionary-7b
+      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: 3.63
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=uukuguy/speechless-zephyr-code-functionary-7b
+      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: 6.71
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=uukuguy/speechless-zephyr-code-functionary-7b
+      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: 11.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=uukuguy/speechless-zephyr-code-functionary-7b
+      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: 23.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=uukuguy/speechless-zephyr-code-functionary-7b
+      name: Open LLM Leaderboard
 ---
 
 <p><h1> speechless-zephyr-code-functionary-7b </h1></p>
@@ -38,3 +133,17 @@ Code: https://github.com/uukuguy/multi_loras
 | GSM8K | 43.82 |
 | Average | 62.93 |
 
+
+# [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_uukuguy__speechless-zephyr-code-functionary-7b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |16.36|
+|IFEval (0-Shot)    |26.96|
+|BBH (3-Shot)       |25.98|
+|MATH Lvl 5 (4-Shot)| 3.63|
+|GPQA (0-shot)      | 6.71|
+|MuSR (0-shot)      |11.61|
+|MMLU-PRO (5-shot)  |23.27|
+