Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

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-2.0

Qwen3-4B RLM RLVR Depth-2 Recursive LoRA Adapter

LoRA adapter from the 150-step depth-2 recursive RLM RLVR run.

  • Base model: Qwen/Qwen3-4B-Instruct-2507
  • Run: rlm-rlvr-qwen3-4b-depth2-recursive-r64-a128-lr1e-5-s150-bal35f40v1
  • Adapter checkpoint: step_150
  • LoRA rank / alpha: 64 / 128
  • Learning rate: 1e-5
  • Training shape: root RLM can call child RLMs; child RLMs use the LLM-only cap prompt.
  • Dataset: lsteno/BEEG-agents, balanced train/eval split used by the run.
  • Uploaded: 2026-06-13T17:49:07.103876+00:00

This repository contains the PEFT adapter files only. Use it with the base model above.

Model provider

lsteno

Model tree

Base

Qwen/Qwen3-4B-Instruct-2507

Adapter

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today