GS1-2B

English · 简体中文

Fast, Faithful, Frontier. GS1-2B is a native typed decision model. Supply state, instructions and runtime candidate meanings; get Choice, Noul and Score distributions with zero generated output tokens.

Code and optimized runtime · Model family · Detailed results

Measurement	GS1-2B
Stored parameters	2,319,227,200
Public Decision Index, 37 benchmarks	62.22
JevBench public task accuracy, 231 decisions	80.09%
AG News test accuracy, 7,600 decisions	91.83%
ToolACE selection accuracy, 640 decisions	93.91%
Warm complete CUDA Graph decision P50 / P95	18.64 / 18.69 ms
Peak allocated GPU memory in that latency fixture	10.60 GiB

Decision Index: complete public edition 0.3, 115,479 unique requests and 279,333 decisions, 100% final coverage, BF16 native reference computation. This is a public score, separate from private Full scores. The three regular benchmarks were measured on 9 November 2026 with zero failures or retries. JevBench public task accuracy is separate from the sealed composite. ToolACE measures first-tool/no-tool selection on a fixed hash subset, not tool-argument generation.

Latency measured on 9 November 2026: RTX 4090 reporting 48 GiB, BF16 computation, 256-token longest branch, one question, single GPU, five warmups and 30 measured calls. Complete in-process timing includes validation, compilation, model computation and probabilities; loading, graph capture, HTTP and SDK transport are excluded. Machine-readable decision metrics · Raw latency samples · Methodology and all models

Default Hugging Face inference

No installation or import of the GS1 repository is required. Use Python 3.11+ and install this folder's dependencies:

python -m pip install -r requirements.txt

from transformers import AutoModel

model = AutoModel.from_pretrained(
    "bigai/GS1-2B",  # a local GS1-2B directory also works
    trust_remote_code=True,
).eval().to("cuda")

result = model.decide(
    state="A customer was charged twice and asks for a refund.",
    questions={
        "team": {
            "type": "choice",
            "instructions": "Choose the team that should handle this ticket.",
            "criteria": {"billing": "Payments and refunds", "technical": "Software problems"},
        },
        "refund": {"type": "noul", "instructions": "Does the customer request a refund?"},
        "urgency": {
            "type": "score",
            "instructions": "Rate the urgency of handling this ticket.",
            "criteria": ["Routine", "Soon", "Immediate"],
        },
    },
)
print(result["answers"])

This works from a local release directory before the Hub upload as well. trust_remote_code=True loads the model code supplied in this folder. Default loading preserves the checkpoint's mixed storage dtypes; avoid a blanket dtype conversion when reproducing the measured precision policy. On a CPU-compatible PyTorch installation, use .to("cpu") and decide(..., precision="fp32"). Optional upstream CUDA kernels can be installed for faster eager inference; the measured stack uses flash-linear-attention[cuda]==0.5.2 and causal-conv1d==1.7.0.

result contains model, answers and usage. Choice returns a candidate ID, a probability for every candidate, and confidence. Noul returns p(true). Score returns the expected zero-based rubric level and probabilities over all supplied levels. Output-token usage is zero. The default path evaluates complete question branches independently and has no runtime profile or graph-capture dependency.

Optimized GS1 inference

The GS1 repository provides source-bound CUDA Graph replay, compatible batching, shared-state reuse, HTTP serving and a playground for these same weights.

git clone https://github.com/bigai-nlco/GS1.git
cd GS1
uv sync --locked --extra serve --extra cuda
uv run gs1 serve --model bigai/GS1-2B --model-name GS1

From the source checkout, install --extra eval in addition to the serving/CUDA extras, then qualify the installed model, hardware and request geometry before enabling graphs:

uv run python -m benchmark.inference --model bigai/GS1-2B \
  --out runs/runtime.json --runtime-profile-out runs/profile.json \
  --graph-cache-mb 16384 --graph-cache-entries 128

uv run gs1 serve --model bigai/GS1-2B --model-name GS1 \
  --runtime-profile runs/profile.json --experimental-cuda-graphs \
  --graph-warmup-requests runs/profile-warmup.json \
  --graph-cache-mb 4096 --graph-cache-entries 128

The benchmark writes profile-warmup.json. Serve known warmed graphs, with native eager fallback for graph misses and single-reference fallback for unqualified geometries. Regenerate the profile when code, model, precision or hardware changes. These profiles belong to the local runtime and are not uploaded as model weights. Full inference guide

Architecture and numerical policy

GS1-2B has width 2,048, 24 decoder layers and 8 decision-attention heads. It combines a Qwen3.5 hybrid GDN/attention backbone, segmented bidirectional full attention, carry-preserving Attention Residuals and a native cross-attention decision head with two routing layers and a 256-dimensional final comparison space. There is no language-generation output head. Candidate meanings are supplied at inference time rather than fixed to a task-specific classifier vocabulary.

Persistent text/head weights are FP32 and the retained vision tower is BF16; the checkpoint specifies BF16 head computation. Final logits/probability reductions are FP32. Complete branches support up to 65,536 tokens subject to explicit admission and memory budgets; the default HTTP service uses a tighter 4,096-token limit. The published decision results are text-only. Model definitions, token IDs and inference_limits are in config.json; all safetensors keys and dtypes are preserved.

Scope and license

Use for routing, classification, tool selection, bounded judgments and other typed decisions. A returned probability is not a guarantee of correctness; calibration depends on the task distribution. The public results include limitations such as low HLE accuracy and zero AA-Omniscience non-hallucination rate at larger sizes when confidence rejection is disabled; inspect all component results.

Code and released weights: Apache-2.0, with upstream attribution. This folder contains model architecture and inference dependencies. Evaluation inputs and local runtime profiles are distributed separately.

@techreport{zheng2026gs1,
  title={GS1: Fast, Faithful, Frontier System One Intelligence},
  author={Zheng, Zilong and Liu, Yang and Qin, Shuhan and Lin, Ziyong and Li, Jiaqi and Jia, Zixia and Zhu, Song-Chun},
  institution={BIGAI},
  year={2026}
}