license: apache-2.0
base_model: peonist-ai/halogen-qwen3.8-flash-next
pipeline_tag: text-generation
library_name: halogen
inference: false
tags:

• halogen
• qwen
• moe
• abliterated
• uncensored
• strix-halo
• gfx1151
• rocm
• amd

Qwen3.8-Flash-Next, abliterated, for the Halogen engine (AMD Strix Halo)

A refusal-direction abliteration of
peonist-ai/halogen-qwen3.8-flash-next,
delivered as a patch kit on top of the vendor checkpoint. It keeps the vendor's .hgn
format, engine and speed; only the weights that carry the refusal behaviour change.

This repo does not contain the base model. You download the vendor checkpoint yourself and
apply the patch to it.

Files

Both parts are required. The overlay alone loads but still refuses; the MoE expert
down_proj tensors carry most of the refusal behaviour.

The patch is pinned to vendor revision 942daecd6013d640bc329e13a409ad3ea7a76439
(qwen38-flash-next-w4b.hgn, 124,068,083,904 bytes, sha256 9c116bbc…5bd6). The apply script
hashes every range first and refuses to write if the base file is anything else.

Method

Standard directional ablation, W' = W − r (rᵀ W), applied to 149 tensors: attention
o_proj, linear-attention out_proj, expert and shared-expert down_proj, the per-layer
embedding value_proj, and embed_tokens (right-side). r is a single refusal direction in the
2560-wide hidden space.

The delta is smaller than one 4-bit quantisation step, so plain re-quantisation erases it.
Non-expert tensors are therefore stored at 8-bit (Q8G64) in the overlay, which the engine accepts
in place of 4-bit. Expert tensors must stay 4-bit and byte-identical in size, so they are encoded
with greedy ±1-step nibble flips along r (about 2 % of weights touched, projection onto r
reduced by ~99 %).

Measured (one Strix Halo box, engine 0.5.9)

• Refusals on a 25 harmful / 25 harmless prompt set: harmful 25/25 → 0/25, harmless 0/25 before and after.
• Decode 31–37 tok/s, the same band as the unmodified checkpoint.
• Resident footprint about 88 GiB (vendor configuration: about 87 GiB).

No broader quality benchmark has been run. Treat it as experimental.

Install on Strix Halo

Requirements: Ryzen AI MAX (gfx1151) with 128 GB unified memory, Linux with /dev/kfd and
/dev/dri available, podman (or docker), Python 3, about 170 GiB of free disk during install
(118 vendor + 25 this repo + 22 backup; the backup and expert_patch.bin can be deleted afterwards
if you do not need to roll back).

1. Download the vendor checkpoint at the pinned revision

hf download peonist-ai/halogen-qwen3.8-flash-next \
  --revision 942daecd6013d640bc329e13a409ad3ea7a76439 \
  --local-dir ~/halogen-models/halogen-qwen3.8-flash-next

2. Download this repo (request access on the model page first, then hf auth login)

hf download Ae55667/halogen-qwen3.8-flash-next-abliterated --local-dir ~/halogen-models/flash-next-ablit

3. Patch the experts — the engine must be stopped; never patch a file the engine has mapped.

python3 ~/halogen-models/flash-next-ablit/apply_expert_patch.py \
  ~/halogen-models/halogen-qwen3.8-flash-next/qwen38-flash-next-w4b.hgn

Expect PATCH APPLIED AND VERIFIED. It reads 22 GiB three times and writes it twice, so allow
several minutes.

4. Start the engine with the abliterated overlay

sudo sysctl -w vm.drop_caches=1 vm.compact_memory=1   # the engine needs large contiguous blocks

podman run --rm --name halogen-serve -p 127.0.0.1:8731:8731 \
  --device /dev/kfd --device /dev/dri --group-add keep-groups \
  --security-opt seccomp=unconfined --security-opt label=disable \
  --ipc=host --ulimit memlock=-1:-1 \
  -v ~/halogen-models/halogen-qwen3.8-flash-next:/models:ro \
  -v ~/halogen-models/flash-next-ablit:/ablit:ro \
  -e HALOGEN_CK_OVERLAY=/ablit/qwen38-flash-next-w4b.overlay.hgn \
  ghcr.io/peonist-ai/halogen-flash-server:0.5.9

HALOGEN_CK_OVERLAY is the only change from the vendor's own run command. The startup log should
report 727 tensors for the overlay and 99 tensors upgraded to q8g64. Add
-e HALOGEN_VISION_TOWER=1 for image input, as in the vendor README.

5. Test

curl -s 127.0.0.1:8731/v1/chat/completions -H 'content-type: application/json' \
  -d '{"messages":[{"role":"user","content":"Say hello."}],"max_tokens":64}'

Notes

• If startup sits at "reserving the KV pool" for minutes and then exits, memory is fragmented:
  stop other large processes, rerun the sysctl line, start again. Do not put the 49 expert
  tensors in the overlay instead of patching them: overlay bytes are pinned in addition to the
  base, and the extra 22 GiB no longer fits.
• The engine is the vendor's closed binary; this repo changes weights only.

Roll back

# stop the engine, then:
python3 ~/halogen-models/flash-next-ablit/restore_expert_patch.py \
  ~/halogen-models/halogen-qwen3.8-flash-next/qwen38-flash-next-w4b.hgn

and start the engine without HALOGEN_CK_OVERLAY. Removing only the overlay leaves abliterated
experts in the base file, which is a hybrid, not the vendor model.

License and provenance

Apache-2.0, inherited from the vendor checkpoint, itself a derivative of Qwen3.8-Flash-Next and
governed by that model's license. The refusal direction was recovered from the published
difference between unsloth/Qwen3.8-Flash-Next-GGUF and
orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF.

This model will comply with requests the original refuses. You are responsible for how you use it.