Downloads · 30 days
30
40% of all-time downloads
lsteno/Qwen3-4B-Instruct-2507-RLM-RL-depth1-r4-a8-lr5e-7-s150-lora
Qwen3-4B-Instruct-2507-RLM-RL-depth1-r4-a8-lr5e-7-s150-lora is a machine learning model from lsteno. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter from the first rank/LR ablation run.
Downloads · 30 days
30
40% of all-time downloads
All-time downloads
75
Public
Repo size
33.1 MB
Likes
0
Public
Click a slice to open those files.
.safetensors33.1 MB · 100%
From the Hugging Face model README
LoRA adapter from the first rank/LR ablation run.
Qwen/Qwen3-4B-Instruct-2507rlm-rlvr-qwen3-4b-depth1-llmonly-r4-a8-lr5e-7-s150sanjaya_text_depth1_llm_only_v1max_depth = 0, plain llm_query subcalls enabled)run_default/broadcasts/step_150The run_configs/ directory contains the exact trainer and orchestrator TOML files saved with the run.