← back to catalog · registered 2026-11-13 22:03

johnlockejrr/ThinkingCap-Qwen3.8-Flash-Next-abliterated-HGN

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/johnlockejrr%2FThinkingCap-Qwen3.8-Flash-Next-abliterated-HGN"
Response includes
  • classification m1
  • files 14
  • author_summary 3 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
97
Likes
2
Model age
1w ago
created 2026-11-13
Downloads over time
Now 97 → from 0 ↑ 0%
03671107 0 on Nov 13 97 on Nov 22 Nov
Nov 13 → Nov 22 · 10 snapshots · spans 9 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
other
Tags
halogen qwen4_exp halogen-flash qwen qwen3.8 flash-next thinkingcap abliterated moe mixture-of-experts quantized hgn

Related

Total size
0 B
Files
14
Quantizations
1
Registered
2026-11-13 22:03
Last updated on HF
2026-11-13 21:45

Files by quantization

Auxiliary files 14 files 111 GB
model.hgn 62.1 GB 85aa0010 download
qwen38-flash-next-ngram.hgn 47.7 GB 339f5c50 download
qwen38-flash-next-vision.hgn 856 MB b6ca6716 download
thinkingcap_demo.mp4 38.4 MB a6d40fc8 download
conversion-manifest.json 3.33 MB 701845c7 download
cap_header.png 1.92 MB 5d972571 download
README.md 8.86 KB c80cf945 download
config.json 4.63 KB 491017e9 download
LICENSE 3.16 KB 9557a896 download
.gitattributes 1.82 KB d9409710 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
sha256.txt 265 B e329c2c5 download
LINK 0 B e69de29b download

README current version from Hugging Face


license: other
license_name: qwen-community-license-1.0
license_link: LICENSE
base_model: bottlecapai/ThinkingCap-Qwen3.8-Flash-Next
base_model_relation: quantized
pipeline_tag: text-generation
library_name: halogen
inference: false
tags:

  • halogen
  • halogen-flash
  • qwen
  • qwen3.8
  • flash-next
  • thinkingcap
  • abliterated
  • moe
  • mixture-of-experts
  • quantized
  • hgn
  • bf16-to-hgn
  • token-efficient
  • efficient-thinking

ThinkingCap — BottleCap AI

ThinkingCap Qwen3.8-Flash-Next — abliterated Halogen HGN (v2)

Native Halogen .hgn weights for
halogen-flash-server,
built from
bottlecapai/ThinkingCap-Qwen3.8-Flash-Next
BF16 after a transferred-direction abliteration on the 149 residual-writer
contract (same method Quat3rnion used for Swift 1.5), then converted with
bf16-to-hgn profile v2 (calibration-free).

These weights are Halogen’s .hgn format and will not load in Transformers,
vLLM, llama.cpp, or similar.
Mount them into a halogen-flash-server
container (or equivalent Halogen runtime).

Hub upload:
johnlockejrr/ThinkingCap-Qwen3.8-Flash-Next-abliterated-HGN.

Sibling packs:

Pack Hub
ThinkingCap v2 (no abliteration) johnlockejrr/ThinkingCap-Qwen3.8-Flash-Next-HGN
ThinkingCap calibrated RCO johnlockejrr/ThinkingCap-Qwen3.8-Flash-Next-calibrated-rco-HGN

What was done

  1. Direction transfer (BF16, CPU/NumPy, no GPU load)
    Quat3rnion’s audited refusal direction r (2560-d, from stock Qwen vs
    orcarouter/Qwen3.8-Flash-Next-Uncensored,
    published under his Swift abliteration
    abliteration/manifest.json)
    was projected onto ThinkingCap’s 149 residual writers (attn outs / expert
    downs / shared downs / MTP writers / PLE value / embeds). Non-writers were
    copied unchanged. Tooling:
    thinkingcap_bf16_abliterate.py (wrapper around his swift_bf16_abliterate.py
    contract). Output BF16:
    /opt/halogen/ThinkingCap-Qwen3.8-Flash-Next-abliterated-bf16 with
    abliteration-manifest.json (status: complete, gates passed).

  2. Halogen convert (no calibrated GPTQ)
    That abliterated BF16 → HGN with bf16-to-hgn CUDA, --profile v2, policy
    bf16-hgn-v2-rtn-nf4-signed-rms-trellis-v1. Abliteration already moves
    weights; we did not add --quality calibrated (plain ThinkingCap HGN
    already beat calibrated on our tool-eval board).

This is not a full heretic Optuna run on ThinkingCap (that needs a large
VRAM box). It is the same-arch direction implant Quat3rnion validated for
Swift-style finetunes — better than raw orca tensor swap, not as native as
heretic-on-ThinkingCap.

Upstream model (behavior)

ThinkingCap is BottleCap AI’s shorter-thinking post-train of Flash-Next.
Upstream reports ~38.5% fewer thinking tokens on average at ~88.8% vs
~89.8% base accuracy:
ThinkingCap card
and blog.

Abliteration may change refusal behavior and can cost some capability. Treat
refusal removal as empirical / unverified until you re-bench.

What is here

File Size Role
model.hgn 62.11 GiB Trunk + embedded MTP (qwen3.8-flash-next-v2)
qwen38-flash-next-ngram.hgn 47.68 GiB N-gram table (required)
qwen38-flash-next-vision.hgn 0.84 GiB Vision tower (optional; HALOGEN_VISION_TOWER=1)
tokenizer/ — Tokenizer + chat template (from ThinkingCap)
config.json — Model config
conversion-manifest.json — Convert provenance / plan
sha256.txt — SHA-256 of the three .hgn payloads
cap_header.png / thinkingcap_demo.mp4 — Upstream branding / demo

Rough total: ~111 GiB. No separate mtp.hgn. N-gram / vision hashes
match our other Flash-Next v2 packs; only model.hgn is unique to this
abliterated ThinkingCap convert.

How it was made

BF16 edit:  bottlecapai/ThinkingCap-Qwen3.8-Flash-Next
            + Quat3rnion audited r (Swift abliteration manifest)
            → ThinkingCap-Qwen3.8-Flash-Next-abliterated-bf16
            method: transferred-direction abliteration (ThinkingCap target)
            writers: 149-contract (not full heretic)

HGN convert:
source:     ThinkingCap-Qwen3.8-Flash-Next-abliterated-bf16  (HF safetensors, 131 shards)
tool:       bf16-to-hgn 0.1.0  (CUDA, HGN_CUDA_ARCH=86)
profile:    v2
policy:     bf16-hgn-v2-rtn-nf4-signed-rms-trellis-v1
quality:    (default / not calibrated)
hgn-spec:   1.1.0 @ 79e75fd4ae7642478823525b0a3212951f584af5
# 1) BF16 direction transfer (CPU)
cd /opt/halogen/tooling-swift-abl/tooling
OPENBLAS_NUM_THREADS=1 OMP_NUM_THREADS=1 \
  /opt/halogen/.venv/bin/python thinkingcap_bf16_abliterate.py \
  --target /path/to/ThinkingCap-Qwen3.8-Flash-Next \
  --direction /path/to/abliteration/manifest.json \
  --output /path/to/ThinkingCap-Qwen3.8-Flash-Next-abliterated-bf16

# 2) Convert + verify (no --quality calibrated)
BIN=/path/to/bf16-to-hgn-optimal/target-cuda/release/bf16-to-hgn
SRC=/path/to/ThinkingCap-Qwen3.8-Flash-Next-abliterated-bf16
OUT=/path/to/ThinkingCap-Qwen3.8-Flash-Next-abliterated-HGN

$BIN convert --source "$SRC" --output "$OUT" \
  --profile v2 --seed 0 --threads 8 --ht-beam 128 \
  --ht-backend cuda --i4r-backend cuda --q4cp-backend cuda

$BIN verify --source "$SRC" --output "$OUT" --decode-backend cuda \
  > verify-thinkingcap-abliterated-r-transfer.json

This build: convert published successfully; verify
provenance_attested: true (1658 source / 2349 output tensors,
118 785 459 868 payload bytes).

HF inputs do not take --mtp / --vision / --ngram / --assets.

How to run

hf download johnlockejrr/ThinkingCap-Qwen3.8-Flash-Next-abliterated-HGN \
  --local-dir ~/halogen-models/ThinkingCap-Qwen3.8-Flash-Next-abliterated-HGN

podman run --rm -p 8731:8731 \
  --device /dev/kfd --device /dev/dri --group-add keep-groups \
  --ipc=host --ulimit memlock=-1:-1 \
  -e HALOGEN_CHECKPOINT=/models/model.hgn \
  -e HALOGEN_VISION_TOWER=1 \
  -v ~/halogen-models/ThinkingCap-Qwen3.8-Flash-Next-abliterated-HGN:/models:ro \
  ghcr.io/peonist-ai/halogen-flash-server:0.19.1

On Docker, use --group-add video --group-add render. API on :8731.
Server docs: halogen-flash-server.

For greedy tool-eval-bench against Halogen, prefer --parallel 1.

Precision (v2)

Checkpoint ~62.1 GiB, Halogen v2 policy
Routed experts I4R
Dense HT / LM head HT4
Hyper-connection mixers Q6G64
Embeddings / small projections Q4C-P
MTP dense / mixer Q8G64 (in model.hgn)
Vision BF16 sidecar
N-gram FP8G, own file

Credits

SHA-256

85aa001000712cb5191a6eae1ce00bcab94989df2a56423e3fd755a061581b66  model.hgn
339f5c508ca592ee2613ac5c3082587a88991d5592c4160d49a32a6dbdb3f30b  qwen38-flash-next-ngram.hgn
b6ca6716eaab601773f7155701bb09f39c72922caa21620bab577f0281f2ea2a  qwen38-flash-next-vision.hgn

N-gram / vision match sibling Flash-Next v2 packs; only model.hgn is unique to this abliterated convert.

Disclaimer

Community Halogen conversion of direction-abliterated ThinkingCap BF16.
Not an official BottleCap, Qwen, OrcaRouter, Quat3rnion, or peonist release.
Refusal removal and quality are not guaranteed — re-measure on Halogen
(tool-eval, your own probes) before production use. Provide moderation if
you deploy to others.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-13 Upload folder using huggingface_hub 3a79d82 8.9 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration