Two alpha releases of DeepSeek-V4-Flash-DSpark with safety refusals removed (abliterated), offering high throughput and full context support for unfiltered use.
23
No data
4
0
NOASSERTION
2026-07-12
It provides a rare, openly available uncensored model variant with measured performance improvements and a detailed comparison of two different ablitation strategies.
Two different alpha releases. Choose deliberately — they are different weight edits.
| v1.0 alpha | v1.1 alpha | |
|---|---|---|
| Who for | Max ablit / max C1 | Mida / Brikie / Hermes (less skill spill) |
| MTP draft heads | Abliterated | Stock |
| C1 pure | ~57 tok/s | ~50 tok/s (slightly slower) |
| Standing concurrency | often C12 @ 1M | C=4 @ 1M |
| Refusal 32/32 | 100% | 100% |
| HF (gated) | Abliterated-Uncensored | …-v1.1-alpha-Mida-Brikie |
Full chooser + rebuild notes: → RELEASES.md
WARNING: These models have had safety refusals removed. Useful for red-teaming / research / unfiltered local assistants — and you must supply your own guardrails.
Both Hugging Face weight repos are gated (gated=auto) with the same access form:
| Field | Notes |
|---|---|
| Username | May default to your HF username |
| May default to your HF account email | |
| Reason for intended use | e.g. red-teaming, evaluation, research, local assistant |
Plus agreement checkboxes for prohibited uses.
Full agreement: → RESPONSIBLE_USE.md
HF: https://huggingface.co/drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored
| Context | 1,048,576 (nvfp4_ds_mla) |
| C1 pure | ~57 tok/s |
| Refusal | ~100% (32-prompt + hard probe) |
| Weights | L0–9 stock · L10–42 + MTP ablit · λ=3.5 |
hf download
DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.