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
Pyrite Pay support agent — GRPO step 70 (LoRA r64)
LoRA rank-64 adapter on Qwen/Qwen3.6-35B-A3B, trained with Freesolo GRPO on the
Pyrite Pay support-ticket environment. Checkpoint grpo_000070.
Eval (final_eval, N=80, same harness as Haiku 4.5 baseline):
- Support Outcome: 0.687 (Haiku 4.5 zero-shot: 0.544; oracle gpt-5.5: 0.888)
- Tool Safety Checks: 0.938 (Haiku 4.5: 0.975)
Model provider
DavidBShan
Model tree
Base
Qwen/Qwen3.6-35B-A3B
Adapter
this model
Modalities
Input
Video, Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information