license: mit base_model:

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF base_model_relation: finetune quantized_by: AtomicChat pipeline_tag: text-generation library_name: gguf tags:
atomic-chat
deepseek
deepseek41
gguf
gsq
rco
strata
abliteration
refusal-direction

DeepSeek-V4.1-Flash-1017 Without Refusals · GSQ-RCO

These are ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF's GSQ-RCO backbone shards (revision cb02422c900d) with only the residual-writing dense tensors replaced: attention output (attn_output_b), the shared-expert down projection (ffn_down_shexp) and the Engram value projection (engram_wkv). The routed experts are left exactly as ISTA shipped them, so GSQ's learned low-bit rounding of the experts is preserved byte for byte, and each file stays the same size and runs wherever the original runs.
The replaced tensors carry the one-direction edit (EN + RU, strength 2.0) baked into DeepSeek's weights at full precision and quantized to ISTA's exact per-tensor type.
Runs on a single 12 GB GPU with Strata: the backbone sits in system memory and the shared Engram table streams from an SSD, so a 763B model fits a consumer machine.

What changed and what did not

Both files served on Strata, same prompts and template; "→" reads the stock GSQ-RCO rung → this one.

Rung	bpw	Total GB	JailbreakBench (EN)	XSTest (safe refused)	Thinking high (30)	MMLU (500)	KL to stock
`IQ2_XXS`	2.0	249	85.2% → 0.0%	7.6% → 0.0%	27/30 → 0/30	82.8% (p=0.27)	—
`IQ1_M`	1.75	231	88.9% → 0.0%	4.8% → 0.0%	27/30 → 1/30	80.6% (p=0.75)	—

KL is the edit's distribution shift from the stock rung, from Strata's teacher-forced score mode: a top-64 lower bound, so the true KL is a little higher. Measurements, prompts and gates: AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF-metrics (ablit/gsq/).

Running it

Download one rung and ISTA-DASLab's shared Engram file, then serve with Strata:

hf download AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF --include "*IQ2_XXS*" --local-dir ds-unc
hf download ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF --include "*Engram*" --local-dir ds-unc   # the 110 GB lookup table, once
strata launch --model-path ds-unc/DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00001-of-00004.gguf

The Engram file is identical to ISTA-DASLab's and is not re-hosted here; keep it on a fast SSD next to the shards. As of this writing these files run in Strata (DeepSeek-V4.1 with a separate Engram file is not yet in llama.cpp).

Limitations

The refusal classifier reads the start of an answer, so a soft refusal later in the text can pass as an answer.
The edit removes refusals across topics; it does not keep a narrower set of them.
With thinking on, the edit plans an answer to a request the original declines, and the plan can be long; give such requests a larger token budget or a lower effort.

Responsible use

This model answers requests the original declines. You are responsible for how you use it and for following the laws that apply to you.

Credits and license

Base model: deepseek-ai/DeepSeek-V4.1-Flash-1017 — MIT (its LICENSE ships here).
GSQ-RCO quantization and the shared Engram file: ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF (DASLab, IST Austria).
Runtime: Strata.

MIT, as the base model and ISTA-DASLab's GGUFs. Built by AtomicChat.

DeepSeek-V4.1-Flash-1017 Without Refusals · GSQ-RCO

These are ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF's GSQ-RCO backbone shards (revision cb02422c900d) with only the residual-writing dense tensors replaced: attention output (attn_output_b), the shared-expert down projection (ffn_down_shexp) and the Engram value projection (engram_wkv). The routed experts are left exactly as ISTA shipped them, so GSQ's learned low-bit rounding of the experts is preserved byte for byte, and each file stays the same size and runs wherever the original runs.

The replaced tensors carry the one-direction edit (EN + RU, strength 2.0) baked into DeepSeek's weights at full precision and quantized to ISTA's exact per-tensor type.

Runs on a single 12 GB GPU with Strata: the backbone sits in system memory and the shared Engram table streams from an SSD, so a 763B model fits a consumer machine.

What changed and what did not

Both files served on Strata, same prompts and template; "→" reads the stock GSQ-RCO rung → this one.

Rung

bpw

Total GB

JailbreakBench (EN)

XSTest (safe refused)

Thinking high (30)

MMLU (500)

KL to stock

IQ2_XXS

2.0

249

85.2% → 0.0%

7.6% → 0.0%

27/30 → 0/30

82.8% (p=0.27)

—

IQ1_M

1.75

231

88.9% → 0.0%

4.8% → 0.0%

27/30 → 1/30

80.6% (p=0.75)

—

Running it

Download one rung and ISTA-DASLab's shared Engram file, then serve with Strata:

hf download AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF --include "*IQ2_XXS*" --local-dir ds-unc hf download ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF --include "*Engram*" --local-dir ds-unc # the 110 GB lookup table, once strata launch --model-path ds-unc/DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00001-of-00004.gguf

Limitations

The refusal classifier reads the start of an answer, so a soft refusal later in the text can pass as an answer.

The edit removes refusals across topics; it does not keep a narrower set of them.

With thinking on, the edit plans an answer to a request the original declines, and the plan can be long; give such requests a larger token budget or a lower effort.