SSyncDev

Sage-SciPerception

SyncDev model directory · Profile updated Nov 19, 2026

Compare with another model

Sage-SciPerception is Shanghai AI Lab's set of projectors feeding crystals, spectra, biological sequences and biosignals into a language model's input.

Key specifications

Specification score
4.9
License
Open weights

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Open download; licence not yet specified, so treat as research-only. No hosted price.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input

Produces

  • Text output

Capabilities

Open weights

What is Sage-SciPerception?

Sage-SciPerception is not a language model. It is a growing set of small trained projectors from Shanghai AI Laboratory that translate scientific data into the embedding space a language model reads. A crystal structure, an infrared spectrum, a protein sequence or an ECG trace goes through its usual scientific encoder, the projector maps those features into token embeddings, and the language model answers in natural language or a structured format.

The release appeared on 6 November 2026 under the Chinese name 书生·元征.

Released projectors

Each projector is trained for one task and pinned to a specific language model revision recorded in its config.json. Publisher-reported results:

Task Metric Score
JARVIS-DFT formation energy MAD/MAE (higher is better) 15.03
MPBind protein interface sites per-protein F1 61.12%
QM9S structure from spectra Acc@1 49.75%
GUE splice-site classification MCC 87.87%
BEACON ncRNA family accuracy 97.35%
SimXRD crystal system accuracy 63.60%
SciTS ECG classification macro-F1 71.53%
SciTS sleep staging macro-F1 72.01%
ATOM3D protein structure ranking Spearman 35.36%

Read the formation-energy row carefully: the metric is a ratio where higher is better, not an error.

How serving works

The projected vectors are spliced into the language model's fully templated prompt embeddings, including system and assistant prefixes, and sent to vLLM through prompt_embeds on the /v1/completions endpoint. Start vLLM with --enable-prompt-embeds. Feature extraction and projection happen on the client; the server only generates.

That design has consequences:

  • You need the exact language model revision each projector was trained against.
  • Scientific encoders are separate dependencies. The crystal example expects CHGNet 0.3.0 atom states of shape [num_atoms, 64].
  • Task-adapted encoders for DNA, MPBind and ncRNA are not yet included.
  • You can verify a projector loads on CPU before downloading any language model.

Licence and maturity

The licence has not yet been specified for this release. Until it is, treat it as research-only and do not build commercial products on it.

Is it useful for your lab?

If your group already runs one of these encoders, the projector route lets a chat model reason about your data without fine-tuning the whole model. Pick one task you have labelled data for, run the projector against the paired language model, and compare its answers with your existing specialist model, not just with a text-only prompt. Shanghai AI Lab's related language models include Sage S2.1 and Intern-S2-397B; each projector's config.json names the exact model it needs. Other scientific and multimodal models are in the catalogue.

How to evaluate Sage-SciPerception

Compare the model on the work you need to complete.

Tasks and inputs

Sage-SciPerception is listed for Feature extraction, Multimodal. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under the publisher’s model licence. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

No. It is a set of task-specific projectors that feed scientific features into a compatible language model's input embeddings.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

NVIDIA

Alpamayo 2 Edge

Alpamayo 2 Edge is NVIDIA's open 2B-class driving VLA that outputs trajectories with causal explanations, sized for DRIVE AGX Thor in-vehicle use.

— context

inclusionAI

Ling 3.2 Flash

Ling 3.2 Flash is inclusionAI's 560B-A25B multimodal MoE with a 1M-token window, built for visual agents, 3D tasks and medical image reasoning.

1M context

Swiss AI

Apertus 1.5 8B

Apertus 1.5 8B is the Swiss AI Initiative's open multilingual model, now taking text, images and audio with a 262K-token context window.

262.14K context

kyutai

REKI-2B

REKI-2B is Kyutai's open 2.4B robot vision-language-action model with cheap register-token memory, pretrained only on public data.

— context

black-forest-labs

FLUX 3 Action

FLUX 3 Action is Black Forest Labs' open 7B world action model for robots, predicting action chunks and future video from cameras, state and text.

— context