dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8
image-text-to-text model by dealignai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://twitter.com/dealignai) [](https://twitter.com/jordanschenck) Uncensored release · Native FP8 (e4m3) + FP4 experts · 40-layer MoE · 1M context · Vision + video · Reasoning tiers · Tools This is deepseek-ai/DeepSeek-V4.1-Flash-1017 with its refusal behavior removed, so the model complies with user requests across topic categories rather than declining them. All upstream capabilities — vision, video, reasoning-effort tiers, tool calling, DSpark speculative decoding, and the native 1M-token context — are preserved. The format on disk (FP8 e4m3 weights + ue8m0 block scales, FP4 experts, 48 safetensors shards, DeepSeek's reference inference/ and encoding/) is byte-compatible with upstream; everything that loads the base model loads this one. ue8m0 block scales and FP4 experts — the same precision DeepSeek ships. No Q80, no Q4, no intermediate GGUF conversion. no enablethinking=false trick. The upstream encoding/ prompt renderer is shipped unchanged. Serves cleanly with no system message or with your own. There is no "turn uncensoring on/off"…
Read the full model card ↗ · Preview checked 2026-10-28T03:56:50.718Z
Inside the original model card — Document outline
- Released by @dealignai · Compute generously provided by @jordanschenck
- DeepSeek-V4.1-Flash-1017 — UNCENSORED (FP8)
- What this is
- What this is NOT (no shortcuts)
- Internal benchmarks (greedy T=0, this repo)
- Capability — MMLU logit (57 subjects × 20 Q, 1140 Q total)
- Compliance — HarmBench-320 (effort=max, FINAL)
- Early smokes (both passed before the full runs)
- How to run
- Hardware
- Build toolchain (reference engine kernels)
- Serving (SGLang)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 is a image-text-to-text model repository published by dealignai on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 11,505
- Cumulative likes
- 509
- Hugging Face trending score
- 108
- Reported safetensors parameters
- 763,205,315,794
- Architecture
- DeepseekV41ForCausalLM
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-10-18T04:11:31.000Z
- Last modified
- 2026-10-18T12:45:29.000Z
Compatibility and lineage
Reported languages: en, zh, es, fr, ru, it, th
Reported base models: deepseek-ai/DeepSeek-V4.1-Flash-1017
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:49:30.141Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.