rskill-rldx1_ft-widowx-simpler_env-nf4

Requires OpenRAL Pro. This rSkill runs at int4 (NF4) (sub-16-bit weights). Under ADR-0123, open-source OpenRAL loads only fp32, fp16 and bf16 weights; quantized formats (int8, fp8, int4/NF4, nvfp4) need the OpenRAL Pro quantization package.

RLDX-1 finetuned on the SIMPLER WidowX benchmark (real-to-sim correlator), packaged for OpenRAL.

This is a sibling of rldx1-ft-libero-nf4; that README owns the canonical architecture, license, auto-managed sidecar lifecycle, and NF4 quantization documentation for every member of the RLDX-1 family. Read it first.

The skill-specific differences from the canonical sibling:

• Upstream weights: hf://RLWRLD/RLDX-1-FT-SIMPLER-WIDOWX.
• Benchmark target: SIMPLER WidowX (real-to-sim correlation for the Bridge / WidowX evaluation protocol).
• Same NF4-on-backbone, bf16-on-head quantization recipe; same sidecar boot path; same non-commercial license posture (OPENRAL_ALLOW_NONCOMMERCIAL=1 required for any activation, plus a vendor agreement with RLWRLD for commercial deployment).

Upstream: https://huggingface.co/RLWRLD/RLDX-1-FT-SIMPLER-WIDOWX