**Abliterated · No guardrails · PTQ1_0 dense-ternary 1.75 bpw · 5.9 GB · Runs on a laptop / single GPU · Vision-capable** > ⚠️ **Re-download notice (2026-09-17 20:44 PDT / 2026-09-18 03:44 UTC)** — an earlier build of this model had a coherence bug in reasoning modes (`low`/`xhigh`) that could cause token loops on some prompts. This version fixes it. If you downloaded before this timestamp, please pull the latest .gguf. Bonsai 2 27B — PrismML's ternary compression of Qwen3.8-27B — with the refusal circuitry surgically removed at the weight level while capability, vision, reasoning modes (`off`/`low`/`xhigh`), tool use, and multi-turn coherence are preserved. Full 27B-class hybrid Attention + SSM (GatedDeltaNet) architecture in a **5.9 GB** 1bit GGUF.
번역 대기 중 · 원문 표시
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
**Abliterated · No guardrails · PQ2_0 ternary 2.13 bpw · 7.2 GB · Runs on a laptop / single GPU · Vision-capable** > ⚠️ **Re-download notice (2026-09-17 20:44 PDT / 2026-09-18 03:44 UTC)** — an earlier build of this model had a coherence bug in reasoning modes (`low`/`xhigh`) that could cause token loops on some prompts. This version fixes it. If you downloaded before this timestamp, please pull the latest .gguf. **Proprietary weight-level abliteration** by the dealignai research team. Byte-identical to the base ternary quant everywhere except a small set of tensors that carry the refusal circuit. Drop-in replacement for the ternary base at inference — same tokenizer, same chat template, same reasoning modes, same vision projector interface.
번역 대기 중 · 원문 표시
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
a **CRACK** release by dealignai · Twitter @dealignai > [!IMPORTANT] > **Runtime notes** — field-tested on 8× DGX Spark GB10 by @0xMagnus (discussion): > > - **`reasoning_effort` only honors `"low"` and `"high"`.** Every other value — `off`, `medium`, `max`, unset, or an unquoted YAML `off:` (parses as boolean `false`) — falls through to `max`. There is no way to disable reasoning on this checkpoint; pass `"low"` for minimum. > - **On FP8, prefer `low` for agent / tool-loop use.** At `high`/`max` the model can spend the whole `max_tokens` budget inside ` ` and return zero answer tokens (finish=`length`); sampling params (temp 0 + rep 1.05, temp 0.7 / top-p 0.95) do not rescue it. It is budget exhaustion, not a loop. If you must run `high`/`max`, give `max_tokens ≥ 8000`. > - **Reasoning text is in `message.reasoning`**, not `message.reasoning_content`. > - **MTP:** non-functional on stock vLLM, but reported working on ciprianveg's B12X sparse-MLA vLLM fork with `--draft-attention-backend B12X_MLA_SPARSE` (+48% decode on coding prompts). > - **1M context via decode-context-parallel is closed** on `glm_moe_dsa` in vLLM today (DSA indexer `k_cache` is replicated across DCP ranks while MLA KV is sharded → `page size is not divisible by target page size and cannot be padded` for `fp8_ds_mla`). Practical TP8 H200 ceiling: ~131K w/MTP, ~160K w/o. Pipeline-parallel (PP2 × TP4) profiles fine, but the MTP draft does not implement `SupportsPP`. **This is a CYBERSECURITY-DOMAIN CRACK of GLM-5.3-FP8 — not a general-purpose uncensor.**
번역 대기 중 · 원문 표시
입력 텍스트→ 출력 텍스트
> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build
번역 대기 중 · 원문 표시
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
**Standard dense Llama-family 33B · 52 layers · 7168 hidden · GQA 56Q/8KV · think on/off · 512K context** > **UNCENSORED** = refusal-removed GGUF build of **Nanbeige/Nanbeige4.3-33B**. Three quants in one place: **Q6_K (25.3 GB)**, **Q4_K_M (18.7 GB)**, **IQ2_XXS (8.7 GB)**. All ship with a fresh matching importance matrix (imatrix) over 1M tokens of mixed code / reasoning / agentic / terminal / conversation calibration content, with exact source-tokenizer parity against the pinned llama.cpp runtime. Native thinking mode (on/off) preserved from the original chat template. > Research artifact for alignment work. This model answers requests the base refuses, including harmful ones. **Do not deploy to end users without separate downstream safety controls.**
번역 대기 중 · 원문 표시
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
입력 텍스트→ 출력 텍스트
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
입력 텍스트→ 출력 텍스트
