No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from dealignai/DeepSeek-V4-Flash-0731-CRACK-NVFP4
All models by dealignai →
[Image blocked: Dealign.ai]
Dealign.ai
Uncensored DeepSeek-V4-Flash-0731 — safety refusals removed while fully preserving knowledge, reasoning (controllable effort), tool-calling, and DSpark speculative decoding. Native FP8 + FP4 (NVFP4-class) checkpoint (~167 GB), built to serve tensor-parallel across two NVIDIA GB10 / DGX Spark nodes.
Research artifact with reduced safety guardrails. Use responsibly and lawfully.
deepseek-ai/DeepSeek-V4-Flash-0731 (43-layer MoE, 256 routed + 1 shared expert, MLA,
sliding-window attention, ~1M context via YaRN). Native quant: FP8 (attention + shared experts)
240 behaviors, answer-channel (no-refusal) compliance, greedy:
Knowledge and reasoning are fully retained — MMLU is within noise (slightly higher). Compliance is measured on the answer channel.
Official DeepSeek-V4-Flash defaults, stamped as this repo's generation_config.json:
These are applied automatically when a request omits sampling params. Override per-request as needed.
Requires the DeepSeek-V4 vLLM path for sm_121 (e.g. the jasl/vllm GB10 build). Head + worker
over a RoCE point-to-point link, TP=2 + expert-parallel, fp8 KV cache, DSpark spec-decode, 384K ctx.
See the included serve/ scripts. Key flags:
Controllable thinking (low / high / max) via the reasoning system preface; the reasoning trace is
returned as reasoning_content, the answer as content. Note: thinking mode reasons at length —
allow ≥2500 output tokens or the answer may be truncated.
DeepSeek-V4 tool-call parser; pass OpenAI-style tools to the chat endpoint.
MIT (inherits the upstream DeepSeek-V4-Flash license terms). Review before use.
{"do_sample": true, "temperature": 1.0, "top_p": 0.95}vllm serve <this-model> --tensor-parallel-size 2 --enable-expert-parallel \ --distributed-executor-backend mp --nnodes 2 --node-rank {0,1} --master-addr <head> \ --kv-cache-dtype fp8 --block-size 256 --enable-prefix-caching \ --max-model-len 393216 --gpu-memory-utilization 0.80 \ --speculative-config '{"method":"dspark","num_speculative_tokens":5}' \ --reasoning-parser deepseek_v4 --tool-call-parser deepseek_v4 --enable-auto-tool-choice