license, library_name, tags, base_model, datasets, model-index

license	library_name	tags	base_model	datasets	model-index
apache-2.0	transformers	qwen2 qwen2.5 dpo chat conversational finetune	Qwen/Qwen2.5-14B-Instruct	jondurbin/gutenberg-dpo-v0.1	name results Qwen2.5-14B-Gutenberg-1e-Delta task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 80.45 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 48.62 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 0.0 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 10.51 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 9.38 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 43.67 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/Qwen2.5-14B-Gutenberg-1e-Delta Open LLM Leaderboard

Qwen2.5-14B-Gutenberg-1e-Delta

---

This is "Qwen2.5-14B-Instruct" trained on jondurbin/gutenberg-dpo-v0.1 for 1.25 epoch's (DPO).

GGUF from QuantFactory:

• GGUF static

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

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