Downloads · 30 days
11
16% of all-time downloads
jakeatx/slimder-qwen38-ream288-ngram50-mixed-recovery-qlora-v2
slimder-qwen38-ream288-ngram50-mixed-recovery-qlora-v2 is a text generation model from jakeatx. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository contains the promoted recovery adapter for jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-mixed-nvfp4-v2.
Downloads · 30 days
11
16% of all-time downloads
All-time downloads
67
Public
Repo size
245 MB
Likes
0
Public
Click a slice to open those files.
.pt163 MB · 57%
From the Hugging Face model README
This repository contains the promoted recovery adapter for
jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-mixed-nvfp4-v2.
The root adapter is the 50k-token checkpoint blended at 62.5% of its trained
LoRA strength (r=8, trained alpha=16, promoted alpha=10). This was the
strongest tested blend that passed every sealed behavior-preservation gate.
The 250k training milestone also improved held-out validation loss from
1.773725 at 50k to 1.596309, but it was not promoted: its sealed token KL was
1.002711, router agreement was 0.834931, and it produced one Japanese
character-loop failure. The full-strength 50k adapter was also not promoted
because token KL was 0.329827. These checkpoints and their evidence are kept
under research-checkpoints/ for reproducibility, not as recommended defaults.
Load the mixed v2 base checkpoint with its included custom runtime, then apply
the adapter in this repository with PEFT. The base uses experimental
qwen4_exp, compact PLE remapping, NVFP4 routed experts, and rowwise FP8 PLE
storage, so it is not a generic drop-in Transformers checkpoint.
evidence/ contains the sealed comparison reports, training state, runtime
validation, precision audits, and hashes. The strengthened qualitative checker
detects both whitespace-token repetition and repeated non-ASCII character
loops.
This is an experimental recovery adapter. It passed the bounded sealed gate, but broad task and safety evaluation are still required before production use.
<!-- qwen38-perian-lineage:start -->This repository is retained in the Qwen3.8 Perian checkpoints collection. Its exact position in the lineage is: Early bounded recovery-QLoRA pilot on the fully compressed mixed base; it predates the final post-training run.
The final Qwen3.8 Perian GGUF release combines three reductions and one post-training stage:
Earlier checkpoints in this collection do not inherit later stages merely by being listed beside them; the stage statement above is authoritative for this artifact.
<!-- qwen38-perian-lineage:end -->