Adding Evaluation Results (#1)

- Adding Evaluation Results (2d46c2302ed20bf9177c93f5759ec9cbd287596d)


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

README.md

@@ -1,6 +1,5 @@
 ---
-base_model:
-- Qwen/Qwen2.5-14B-Instruct
+license: apache-2.0
 library_name: transformers
 tags:
 - qwen2
@@ -9,9 +8,105 @@ tags:
 - chat
 - conversational
 - finetune
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-14B-Instruct
 datasets:
 - jondurbin/gutenberg-dpo-v0.1
+model-index:
+- name: Qwen2.5-14B-Gutenberg-1e-Delta
+  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: 80.45
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta
+      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: 48.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta
+      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=v000000/Qwen2.5-14B-Gutenberg-1e-Delta
+      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: 10.51
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta
+      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: 9.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta
+      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: 43.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta
+      name: Open LLM Leaderboard
 ---
 
 # Qwen2.5-14B-Gutenberg-1e-Delta
@@ -24,4 +119,17 @@ This is "Qwen2.5-14B-Instruct" trained on [jondurbin/gutenberg-dpo-v0.1](https:/
 
 GGUF from QuantFactory:
 
-* [GGUF static](https://huggingface.co/QuantFactory/Qwen2.5-14B-Gutenberg-1e-Delta-GGUF)
+* [GGUF static](https://huggingface.co/QuantFactory/Qwen2.5-14B-Gutenberg-1e-Delta-GGUF)
+# [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_v000000__Qwen2.5-14B-Gutenberg-1e-Delta)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |32.11|
+|IFEval (0-Shot)    |80.45|
+|BBH (3-Shot)       |48.62|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      |10.51|
+|MuSR (0-shot)      | 9.38|
+|MMLU-PRO (5-shot)  |43.67|
+