SSyncDev

Intern-MemDec-4B

SyncDev model directory · Profile updated Nov 19, 2026

Compare with another model

Intern-MemDec-4B is Shanghai AI Lab's biology memory decoder that plugs into Intern-S2 backbones to add DNA, RNA and protein knowledge without retraining.

Key specifications

Specification score
4.4
License
Open weights

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

Pricing conditions: Open download; no hosted price. No licence is stated for the weights, so check the repository before commercial use.

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 Intern-MemDec-4B?

Fine-tuning a big model on biology usually costs you some of its general ability. Intern-MemDec-4B is Shanghai AI Laboratory's way around that alignment tax. Instead of changing the Intern-S2 backbone, it bolts on a separate 4B-class "memory decoder" that knows biology. Both run on the same context in parallel, and a small token-level router decides, at each step, how much each one's prediction counts.

It is not a chat model. Load it on its own and you get nothing useful.

The mechanism

The memory was trained (the method is called MemSFT) to imitate a retriever searching biological data. In effect it memorises what retrieval would have fetched, so at inference time there is no datastore to host or query. On biology prompts the router leans on the memory; on general prompts it keeps the backbone in charge, which is how general reasoning, instruction following and multimodal behaviour are supposed to survive.

Reported effect

With Intern-S2-Preview-397B on all 21 Biology-Instructions tasks, the publisher reports the average rising from 56.92 to 60.32. The detail is more mixed than the average:

Task Backbone alone + memory
Promoter-enhancer interaction 22.46 38.47
RNA CRISPR on-target 6.61 17.18
DNA tf-m 56.96 67.09
Protein thermostability 58.44 53.97
Antibody-antigen 40.24 36.44

Gains are concentrated in DNA and RNA tasks; several protein and interaction tasks get slightly worse. If your work is protein engineering, test before assuming it helps.

Deployment requirements

  • A compatible Intern-S2 backbone, plus the matching router or fusion configuration.
  • Hardware for both models at once. The memory adds roughly 4.5B parameters on top of the backbone.
  • Biology only. Shanghai AI Lab says other domains need separately trained memories.

The underlying paper also shows a trained memory being reused across backbones of different sizes, which is the long-term appeal: swap domain memories in and out instead of maintaining fine-tuned forks.

Evaluating it on your problems

Split your test set by subdomain (DNA, RNA, protein, interactions) and score backbone-only against backbone-plus-memory separately for each. Also rerun a handful of non-biology prompts to confirm general behaviour holds. Related Intern-S2 models in the catalogue include Intern-S2-397B and Intern-S2-Mobius; confirm compatibility against the memory's router configuration before pairing. For a domain model trained end to end, compare with GPT-Rosalind 6. More are listed under language and text.

How to evaluate Intern-MemDec-4B

Compare the model on the work you need to complete.

Tasks and inputs

Intern-MemDec-4B is listed for Language & text, Text generation. 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 must run alongside a compatible Intern-S2 backbone with the matching router or fusion configuration.