lsteno
/

qwen3-rlm-depth1-r16-a32-lr1e-5-s150-bal35f40v1-lora

Model card Files Files and versions

rlm-rlvr-qwen3-4b-depth1-llmonly-r16-a32-lr1e-5-s150-bal35f40v1

LoRA adapter from the depth-1 LLM-only RLM RLVR rank/LR ablation.

Base model: Qwen/Qwen3-4B-Instruct-2507
Run id: rlm-rlvr-qwen3-4b-depth1-llmonly-r16-a32-lr1e-5-s150-bal35f40v1
Adapter source: run_default/broadcasts/step_150
Prompt variant: sanjaya_text_depth1_llm_only_v1
Recursive RLM calls blocked at runtime; plain LLM subcalls remain enabled.

Downloads last month: 2

Inference Providers NEW

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

Model tree for lsteno/qwen3-rlm-depth1-r16-a32-lr1e-5-s150-bal35f40v1-lora

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5700)

this model

Collection including lsteno/qwen3-rlm-depth1-r16-a32-lr1e-5-s150-bal35f40v1-lora

Qwen 3 4B RLM RLVR

Everything from my experiments on training RLMs. • 14 items • Updated 26 days ago