Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: apache-2.0Training
- Stage 0: inherited from v5-5 (
lora-stage0-v5-5-final) - Stage 1 SFT: 1 epoch, LR 5e-5, ~12K rows (cybersec + tool + cursor code engineering)
- Stage 2 SFT: 1 epoch, LR 2e-5, ~6.5K rows (multistep + planning + ballast + inline uncensor + stepback)
- Stage 2.5 DPO: 1 epoch, beta 0.1, LR 5e-7, ~410 pairs
Inference
Use lkjiop8/Yuanl-27B-v5-7-GGUF for ready-to-run MTP GGUF files.
Model provider
lkjiop8
Model tree
Base
Qwen/Qwen3.6-27B
Adapter
this model
Modalities
Input
Video, Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information