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 (continued, on top of v5-7)
- Stage F1 SFT: 2 epochs, LR 2e-5 - hard-task completion + loop-breakout (+optional replay), patience early-stop.
- Stage F2 DPO: 1 epoch, beta 0.1, LR 5e-7 - anti-deathloop + anti-early-termination pairs.
Inference
Use lkjiop8/Yuanl-27B-v5-8-GGUF and the anti-loop launch flags in its README.
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