Downloads · 30 days
12
3% of all-time downloads
Xiaolong-Qwen3-14B
nbeerbower/Xiaolong-Qwen3-14B
Xiaolong-Qwen3-14B is a text generation model from nbeerbower. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
344
Public
Parameters
14.8B
29.5 GB on disk
Likes
9
Public
Repo makeup
Click a slice to open those files.
.safetensors29.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- May 8, 2025
- Updated
- May 9, 2025
- SHA
- 1f900ee4
Try a prompt
Base models
Model card
From the Hugging Face model README
Xiaolong-Qwen3-14B
Xiaolong is a small, uncensored, reasoning-focused model finetuned using ORPO and QLoRA on top of Qwen3-14B-abliterated-TIES.
Finetuning Details
- Method: ORPO
- Epochs: 2
- Learning Rate: 5e-6, cosine decay w/ 5% warmup
- Batch Size: 1 x 32 (32 effective)
- Max Grad Norm: 0.3
- LoRA Rank: 64
- Hardware: 1x NVIDIA RTX A6000
Dataset Composition
~9,100 samples. 3,000 used Chain of Thought reasoning.
- 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 (1000 samples)
- jondurbin/gutenberg-dpo-v0.1
- nbeerbower/gutenberg2-dpo
- nbeerbower/gutenberg-moderne-dpo
Chain of Thought
- GeneralReasoning/GeneralThought-430K (1000 samples)
- nvidia/OpenMathReasoning (1000 samples)
- nvidia/OpenCodeReasoning (1000 samples)
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- May 8, 2025
- Updated
- May 9, 2025