Downloads · 30 days
6
11% of all-time downloads
Triton-VX-Qwen3.5-2B-DPO-LoRA
Fabrix-AI-Inc/Triton-VX-Qwen3.5-2B-DPO-LoRA
Triton-VX-Qwen3.5-2B-DPO-LoRA is a text generation model from Fabrix-AI-Inc. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
LoRA adapter weights for Triton VX Qwen3.5 2B, trained with Direct Preference Optimization (DPO) for Fabrix.ai / RDAF citation retrieval.
All-time downloads
53
Public
Repo size
63.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors43.7 MB · 69%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Aug 26, 2026
- Updated
- Aug 26, 2026
- SHA
- 8ef1ebc8
Try a prompt
Base models
Model card
From the Hugging Face model README
Triton VX Qwen3.5 2B (DPO) - LoRA Adapter
LoRA adapter weights for Triton VX Qwen3.5 2B, trained with Direct Preference Optimization (DPO) for Fabrix.ai / RDAF citation retrieval.
- Base Model:
unsloth/Qwen3.5-2B(or checkpoint-300 SFT model) - Adapter Type: PEFT LoRA (r=16, alpha=32, target_modules:
q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj) - Full Merged Standalone Model:
Fabrix-AI-Inc/Triton-VX-Qwen3.5-2B-DPO
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Aug 26, 2026
- Updated
- Aug 26, 2026