license: other
license_name: openmdw-1.1
base_model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
library_name: transformers
pipeline_tag: text-generation
tags:

• nemotron
• nemotron-3
• nemotron-h
• hybrid
• mamba
• mixture-of-experts
• moe
• nvfp4
• abliterated
• uncensored
• reasoning

Support & Community

OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensored-NVFP4

Overview

NVFP4 weights of Nemotron-3-Ultra-550B-A55B-abliterated-uncensored — an abliterated, uncensored
variant of NVIDIA's Nemotron-3-Ultra-550B-A55B
(550B total / 55B active). The model keeps Nemotron-3's hybrid Mamba-2 / Attention / Latent-MoE
reasoning stack fully intact — including the MTP speculative-decoding head and the enable_thinking
reasoning mode — so this checkpoint is a drop-in replacement for the original at the architecture level
and serves out-of-the-box on vLLM.

The pipeline:

1. Refusal Ablation — A residual-stream refusal direction was extracted by diff-in-means on a
   labeled harmful/harmless prompt set, read at the end of the model's own reasoning trace
   (</think>), then baked into the weights as an offline orthogonal projection on the residual-write
   modules — using our own custom abliteration framework that operates directly on the packed NVFP4
   tensors (dequantize → project → requantize), with no full-precision decompress and no training.

Key Properties:

• Uncensored across the standard refusal axes
• Reasoning preserved (hybrid Mamba/Attention/MoE + MTP; enable_thinking works)
• Coherence & factual accuracy preserved (layer-profiled, capability-orthogonalized edit)
• Native NVFP4 — drop-in shape/format compatibility with the base release; serves on vLLM as-is

Architecture

Files

113 NVFP4 safetensors shards + config.json, model.safetensors.index.json, tokenizer,
chat_template.jinja, generation_config.json. Total on disk: ~329 GB.

Usage (vLLM)

vllm serve OpenYourMind/OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensored-NVFP4 \
  --trust-remote-code \
  --tensor-parallel-size 4 \
  --enable-expert-parallel \
  --max-model-len 262144 \
  --reasoning-parser nemotron_v3

Fits a single node of 4× B200 / B300 (or 8× H100). On large-VRAM Blackwell it also runs at
--tensor-parallel-size 2. Requires vLLM ≥ 0.22.

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="x")
r = client.chat.completions.create(
    model="OpenYourMind/OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensored-NVFP4",
    messages=[{"role": "user", "content": "Your prompt here"}],
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(r.choices[0].message.content)

Best Practices

• Sampling: temperature=1.0, top_p=0.95 (the values in generation_config.json). A mild
  repetition_penalty (~1.1) is recommended for long generations.
• Thinking mode: set enable_thinking=True in chat_template_kwargs; reasoning streams inside
  <think>…</think> before the answer. Do not feed previous-turn reasoning back into multi-turn history.

Hardware

NVFP4 weights are ~329 GB. Single-node 4× B200 / 4× B300 (or 8× H100) for full context;
expert-parallel recommended. Smaller deployments work at reduced context with tensor-parallel-size 2 on
high-VRAM Blackwell cards.

Notes

• License: OpenMDW-1.1 (inherits from the base model)
• Base Model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
• Format: NVFP4 (mixed-precision)
• Architecture: Nemotron-3 Ultra (hybrid Mamba-2 / Attention / Latent-MoE, 550B/A55B)

Thanks

• NVIDIA — for the Nemotron-3 open models.

Disclaimer

Use is the responsibility of the user. Ensure your usage complies with applicable laws, platform rules,
the OpenMDW-1.1 license terms, and your deployment requirements.