Files
ModelHub XC 3d97ba8dcb 初始化项目,由ModelHub XC社区提供模型
Model: lsteno/Qwen3-4B-Instruct-2507-RLM-RLVR-FullFT-lr5e-6-depth1-v1
Source: Original Platform
2026-06-29 17:20:16 +08:00

574 B

base_model, library_name, license, private
base_model library_name license private
Qwen/Qwen3-4B-Instruct-2507 transformers apache-2.0 true

lsteno/Qwen3-4B-Instruct-2507-RLM-RLVR-FullFT-lr5e-6-depth1-v1

Full-parameter RLM RLVR checkpoint.

  • Base model: Qwen/Qwen3-4B-Instruct-2507
  • Source checkpoint: /home/ubuntu/prime_run/outputs/rlm-rlvr-qwen3-4b-depth1-llmonly-fullft-lr5e-6-s150-bal35f40v1-ncclfixed-allrollouts/weights/step_150
  • Step: 150
  • Prompt variant: sanjaya_text_depth1_llm_only_v1
  • Runtime: depth-1 LLM-only RLM harness, plain Gemini subcalls, recursive child RLMs disabled.