Adding Evaluation Results

README.md

@@ -1,12 +1,7 @@
 ---
-datasets:
-- jondurbin/gutenberg-dpo-v0.1
-- Qwen/Qwen2.5-14B-Instruct
-- HuggingFaceH4/ultrafeedback_binarized
-base_model:
-- Qwen/Qwen2.5-14B-Instruct
-- v000000/Qwen2.5-14B-Gutenberg-1e-Delta
-- tanliboy/lambda-qwen2.5-14b-dpo-test
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - qwen
@@ -21,10 +16,110 @@ tags:
 - storywriting
 - roleplay
 - novelwriting
-license: apache-2.0
-language:
-- en
+base_model:
+- Qwen/Qwen2.5-14B-Instruct
+- v000000/Qwen2.5-14B-Gutenberg-1e-Delta
+- tanliboy/lambda-qwen2.5-14b-dpo-test
+datasets:
+- jondurbin/gutenberg-dpo-v0.1
+- Qwen/Qwen2.5-14B-Instruct
+- HuggingFaceH4/ultrafeedback_binarized
 pipeline_tag: text-generation
+model-index:
+- name: Qwen2.5-Lumen-14B
+ 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: 80.64
+ name: strict accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-Lumen-14B
+ 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: 48.51
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-Lumen-14B
+ 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-Lumen-14B
+ 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: 10.4
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-Lumen-14B
+ 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: 10.29
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-Lumen-14B
+ 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: 43.36
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-Lumen-14B
+ name: Open LLM Leaderboard
 ---
 
 # Qwen2.5-Lumen-14B
@@ -226,4 +321,17 @@ The following models were included in the merge:
 -------------------------------------------------------------------------------
 
 - Context Length: Full 131,072 tokens and generation 8192 tokens
-- Qwen2(ChatML) Prompt format
+- Qwen2(ChatML) Prompt format
+# [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-Lumen-14B)
+
+| Metric |Value|
+|-------------------|----:|
+|Avg. |32.20|
+|IFEval (0-Shot) |80.64|
+|BBH (3-Shot) |48.51|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot) |10.40|
+|MuSR (0-shot) |10.29|
+|MMLU-PRO (5-shot) |43.36|
+