VOOZH

URL: https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2

⇱ nbeerbower/Dumpling-Qwen2.5-32B-v2 · Hugging Face

Dumpling-Qwen2.5-32B-v2

nbeerbower/Rombos-EVAGutenberg-TIES-Qwen2.5-32B finetuned on:

Method

QLoRA ORPO tuned with 8x A100 for 2 epochs. Rank 64 LoRA, 2e-5 learning rate.

Downloads last month: 10

Safetensors

Model size

33B params

Tensor type

BF16

·

Model tree for nbeerbower/Dumpling-Qwen2.5-32B-v2

Base model

nbeerbower/Rombos-EVAGutenberg-TIES-Qwen2.5-32B

Finetuned

(2)

this model

Merges

Quantizations

Datasets used to train nbeerbower/Dumpling-Qwen2.5-32B-v2

Collection including nbeerbower/Dumpling-Qwen2.5-32B-v2

Qwen2.5 finetunes aiming for decensorship and improved english prose • 9 items • Updated Jun 9, 2025 • 2