lsteno
/

Qwen3-4B-Instruct-2507-RLM-RL-depth1-r4-a8-lr5e-7-s150-lora

Model card Files Files and versions

Qwen3-4B RLM RLVR Depth-1 LoRA Adapter

LoRA adapter from the first rank/LR ablation run.

Base model: Qwen/Qwen3-4B-Instruct-2507
Run id: rlm-rlvr-qwen3-4b-depth1-llmonly-r4-a8-lr5e-7-s150
Prompt variant: sanjaya_text_depth1_llm_only_v1
Runtime depth: depth-1 LLM-only orchestration (max_depth = 0, plain llm_query subcalls enabled)
LoRA rank: 4
LoRA alpha: 8
Learning rate: 5e-7
Training steps: 150
Final adapter source: run_default/broadcasts/step_150

The run_configs/ directory contains the exact trainer and orchestrator TOML files saved with the run.

Downloads last month: 9

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lsteno/Qwen3-4B-Instruct-2507-RLM-RL-depth1-r4-a8-lr5e-7-s150-lora

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5713)

this model

Collection including lsteno/Qwen3-4B-Instruct-2507-RLM-RL-depth1-r4-a8-lr5e-7-s150-lora

Qwen 3 4B RLM RLVR

Everything from my experiments on training RLMs. • 14 items • Updated 25 days ago