Qwen2.5 finetunes aiming for decensorship and improved english prose • 9 items • Updated • 2
Dumpling-Qwen2.5-14B
nbeerbower/EVA-abliterated-TIES-Qwen2.5-14B finetuned on:
- nbeerbower/GreatFirewall-DPO
- nbeerbower/Schule-DPO
- nbeerbower/Purpura-DPO
- nbeerbower/Arkhaios-DPO
- jondurbin/truthy-dpo-v0.1
- antiven0m/physical-reasoning-dpo
- flammenai/Date-DPO-NoAsterisks
- flammenai/Prude-Phi3-DPO
- Atsunori/HelpSteer2-DPO
- jondurbin/gutenberg-dpo-v0.1
- nbeerbower/gutenberg2-dpo
- nbeerbower/gutenberg-moderne-dpo.
Method
QLoRA ORPO tuned with 4x H100 for 2 epochs.
- Downloads last month
- 6
Safetensors
Model size
15B params
Tensor type
BF16
·
Model tree for nbeerbower/Dumpling-Qwen2.5-14B
Base model
nbeerbower/EVA-abliterated-TIES-Qwen2.5-14BQuantizations
4 models