Skip to page content
SAVRN
Search Plan a project

Open-weight model

rlport-hkl_jord9v_L_pl10_20261018_021952

by Jord Nguyen Jordine/rlport-hkl_jord9v_L_pl10_20261018_021952

rlport-hkl_jord9v_L_pl10_20261018_021952 is an open-weight model from Jord Nguyen. Its published files total 4.9 GB.

Automatic off-box backup of one RL training run from the reward-laundering project (Tinker -> vast port), written by scripts/port/hfbackup.py so a run can resume after its cloud GPU box disappears.

Parameters—
Context—
Weights4.9 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

Automatic off-box backup of one RL training run from the reward-laundering project (Tinker -> vast port), written by scripts/port/hfbackup.py so a run can resume after its cloud GPU box disappears. Contents: LoRA adapters (Qwen3.5, PEFT/Tinker layout) + optimizer state, per-step metrics, training rollouts and logs. Research artifact only; not a model release, not intended for use.

Excerpt from the card by Jord Nguyen.

Identity and Version

Repository
Jordine/rlport-hkl_jord9v_L_pl10_20261018_021952
Publisher
Jord Nguyen
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
ada032f2a0c7ff79504f9cfcc605699016da726a
First published
2026-10-18
Last updated
2026-10-18

Files and Weights

34 files, 4.9 GB in total. The weights are 10 files totalling 4.9 GB in pt, safetensors.

Weights10 files · 4.9 GB
Configuration14 files · 24.9 KB
Documentation4 files · 9.5 KB
Other5 files · 3.5 MB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
kept/sampler_weights__jord9v_L_pl10_hkl_step20/adapter_model.safetensorsWeights378.4 MB ad304082f068
kept/sampler_weights__jord9v_pl10_hkl_step13/adapter_model.safetensorsWeights378.4 MB 40e34878ea3f
kept/sampler_weights__jord9v_pl10_hkl_step5/adapter_model.safetensorsWeights378.4 MB 5ebcb835c204
kept/sampler_weights__jord9v_pl10_hkl_step9/adapter_model.safetensorsWeights378.4 MB a26765526593
kept/weights__jord9v_L_pl10_hkl_state_step20/adapter_model.safetensorsWeights378.4 MB ad304082f068
kept/weights__jord9v_L_pl10_hkl_state_step20/optimizer.ptWeights757.1 MB ece66a79fdef
kept/weights__jord9v_pl10_hkl_state_step13/adapter_model.safetensorsWeights378.4 MB 40e34878ea3f
kept/weights__jord9v_pl10_hkl_state_step13/optimizer.ptWeights757.1 MB d8f8ef0e5cc2
state/latest/adapter_model.safetensorsWeights378.4 MB e27f9e0a1446
state/latest/optimizer.ptWeights757.1 MB ebb9466e21bc
kept/sampler_weights__jord9v_L_pl10_hkl_step20/adapter_config.jsonConfiguration278 B —
kept/sampler_weights__jord9v_pl10_hkl_step13/adapter_config.jsonConfiguration278 B —
kept/sampler_weights__jord9v_pl10_hkl_step5/adapter_config.jsonConfiguration278 B —
kept/sampler_weights__jord9v_pl10_hkl_step9/adapter_config.jsonConfiguration278 B —
kept/weights__jord9v_L_pl10_hkl_state_step20/adapter_config.jsonConfiguration278 B —
kept/weights__jord9v_pl10_hkl_state_step13/adapter_config.jsonConfiguration278 B —
manifest.jsonConfiguration1.2 KB —
run/cli_extras.jsonConfiguration326 B —
run/cmdline.jsonConfiguration595 B —
run/config.jsonConfiguration694 B —
run/resume.jsonConfiguration987 B —
run/summary.jsonConfiguration19.0 KB —
state/latest/_origin.jsonConfiguration123 B —
state/latest/adapter_config.jsonConfiguration278 B —
README.mdDocumentation496 B —
run/eval_steps/step11_four_cell.mdDocumentation3.0 KB —
run/eval_steps/step13_four_cell.mdDocumentation2.1 KB —
run/eval_steps/step5_four_cell.mdDocumentation4.0 KB —
logs/rl_jord9v_L_pl10.logOther6.3 KB —
run/evals.jsonlOther1.4 KB —
run/metrics.jsonlOther25.7 KB —
run/rollouts.jsonl.gzOther3.5 MB 2e3675758aa5
run/state.txtOther102 B —
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
4.9 GB
Download from Jord Nguyen

Released by Jord Nguyen through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published4.9 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.