← back to catalog · registered 2026-09-16 18:56

neko-legends/DeepSeek-V4.1-Flash-uncensored-engram-4x-spark

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
0
Likes
0
Model age
today
created 2026-09-16

Metadata

License
mit
Tags
engram uncensored abliterated deepseek-v4-1-flash dgx-spark sglang license:mit region:us

Related

Total size
189 GB
Files
12
Quantizations
1
Registered
2026-09-16 18:56
Last updated on HF
2026-09-16 18:08

Files by quantization

Auxiliary files 12 files 189 GB
engram-l14-r1of4.bin 23.6 GB f4035319 download
engram-l14-r3of4.bin 23.6 GB 2ccaf709 download
engram-l14-r0of4.bin 23.6 GB e3d99dda download
engram-l14-r2of4.bin 23.6 GB fe79ad35 download
engram-l1-r0of4.bin 23.6 GB d82ab3ab download
engram-l1-r1of4.bin 23.6 GB cdf9750f download
engram-l1-r2of4.bin 23.6 GB a9aba54c download
engram-l1-r3of4.bin 23.6 GB 952583ab download
README.md 3.25 KB ebfcb879 download
manifest.json 1.82 KB e356c7bd download
.gitattributes 1.48 KB a6344aac download
SHA256SUMS 948 B 5865fa2b download

README current version from Hugging Face


license: mit
tags:

  • engram
  • uncensored
  • abliterated
  • deepseek-v4-1-flash
  • dgx-spark
  • sglang

DeepSeek-V4.1-Flash UNCENSORED — Engram tables, pre-packed for 4× DGX Spark (TP=4)

What is this? DeepSeek-V4.1-Flash carries two giant lookup tables the architecture calls
Engram (at layers 1 and 14): ~189 GiB of n-gram-conditioned embeddings the model reads with
a hash lookup on every token, in both prefill and decode. They are the reason the checkpoint is
510 GB but only ~305 GiB is "weights" — the tables are data, not matrix weights: never quantized,
never sharded by tensor shape, never computed on. On a DGX Spark that distinction is life-or-death:
host RAM is the GPU's memory (121.7 GiB unified per node). Park 189 GiB of tables in GPU memory
and nothing fits; put them on NVMe and read rows directly (the kit's Engram row-store, with
OFFLOAD_MODE=nvme), and a 4-node Spark fleet serves the full frontier model with room for a
1M-token context on top.

These are those tables, already packed into each rank's NVMe-resident binary shards — the
output of Mia's pack_engram.py (the slow, all-read step you'd otherwise run once per node).
Download → drop in → boot.

Packed from the abliterated checkpoint
dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8
with Mia AI Lab's 4×-Spark kit
(SGLang, TP=4, EP=4, RoCE rail). Engram content follows the weights: do not use these shards
with the standard deepseek-ai checkpoint — let the kit pack its own (./start.sh pack).

Who can use this

  • 4× DGX Spark, TP=4, Mia's kit, the dealignai UNCENSORED-FP8 checkpoint: download, drop in,
    boot. Skips the ~7–10 min/node pack step. Verify with sha256sum -c SHA256SUMS.
  • TP=3 or other engines: re-pack from the checkpoint with pack_engram.py --tp N instead —
    the shard layout partitions table rows by rank (each file = one rank's contiguous row range).

Provenance & gates

Packed 2026-09-15 from kit commit 79f656a. The world these shards came from passed our full
gate suite before serving: DSML tool-corruption repro 3/3, 30/30 structured outputs across
temp 0/0.7/1.0, tool round-trip 3/3, reasoning mode engages, context needle at 32k/400k.
Full protocol, numbers, and the operational fixes the recipe didn't mention are in the companion
repo: github.com/neko-legends/spark-bench
section DeepSeek V4.1 Flash — SGLang.

Files

file layer rank size
engram-l1-r{0..3}of4.bin 1 0–3 23.6 GiB each
engram-l14-r{0..3}of4.bin 14 0–3 23.6 GiB each

Total 192 GB. Each node needs only its own rank's two files (~48 GB).

Install

# on each node
mkdir -p ~/dsv41-engram-unc     # ENGRAM_DIR (head) / $WORKER_ENGRAM_DIR (workers)
huggingface-cli download neko-legends/DeepSeek-V4.1-Flash-uncensored-engram-4x-spark \
  --include "engram-*-r${RANK}of4.bin" --local-dir ~/dsv41-engram-unc
sha256sum -c SHA256SUMS --ignore-missing
# kit knobs: ENGRAM_DIR / WORKER_ENGRAM_DIR point there, DSV41_PACKED_DIR=/engram, SKIP_PREPARE=1

Exact hashes, sizes, and layout in manifest.json.

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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.