Overview
| Name | AMPLIFY · aliases: AMPLIFY, AMPLIFY 350M, AMPLIFY 120M |
|---|---|
| Full name | The name is a model codename with no expanded form in the paper |
| Ambiguous names (not auto-linked) | Amplify |
| Family | Not a family entry. 120M and 350M are two sizes of one model, not separate members |
| Organization | Mila, Polytechnique Montréal, Amgen |
| Organization type | Mixed · A joint project of an academic institute and a university lab with a large biopharma company's research arm |
| Country | Canada, United States |
| Model class | Protein language model (small scale) |
| Domain | Proteins |
| First release | · preprint Basis: Preprint v1 posted; the 2024-09-19 first commits and 2024-09-30 weights do not count as first release source |
| Other milestones | |
| Latest update | · paper revision Basis: Preprint v2 revision Paper revised to v2 (v1 was 2024-09-23); no journal version, and the repository and model hub carry only minor changes with the last default-branch commit on 2025-07-17 source The most recent sourced event, not a claim that nothing changed since. |
| Status | Maintained only · Only a paper revision and minor code changes, no new generation |
| Openness | Code: Open Weights: Open · MIT Code, data and weights are all public and the model card gives MIT for the weights; another page says Apache 2.0, so the conflicting code terms are left empty |
| Benchmarks reported | 0 counted · none of the 44 |
| Wet-lab validation | None recorded |
| Unverified fields | † claimed_advantage, open_status.code_license, release_milestones.code_release, release_milestones.weights_release |
| As of | 2026-11-16 |
What it does
Uses a modern architecture, cleaned and debiased training data and an efficient codebase to train protein language models far smaller than their contemporaries, to test whether bigger is always better. It is a research baseline rather than a product, positioned against the scale-first route of ESM3 and ESM C.
Benchmarks reported
None of the 44 benchmarks. This model is on the zero-pairing list.
How it evaluates itself: Held-out UniProt pseudo-perplexity; Masked-residue sequence recovery; Unsupervised contact prediction; Disorder discrimination; Inference throughput and design pipeline
Other evaluations (outside the 44)
- Held-out UniProt pseudo-perplexity (Comparison against baselines only) Self-reported: Held-out likelihood against existing protein language models at several scales, claiming the small model is competitive with the largest baseline
- Masked-residue sequence recovery (Own task set) Self-reported: Recovery on the human proteome grouped by conservation plus a long-context extension, including the authors' own retrained controls
- Unsupervised contact prediction (Public benchmark not among the 44) Self-reported: Attention-map contact prediction with logistic regression and random forest: the baseline is better with logistic regression and the gap shrinks with random forest
- Disorder discrimination (Public benchmark not among the 44) Self-reported: Discrimination of a disorder database against hypothetical proteins, with embedding similarity compared to structure-prediction confidence
- Inference throughput and design pipeline (Comparison against baselines only) Self-reported: Proteins per second on one GPU, claimed more than an order of magnitude faster than the largest baseline, plus sequence recovery in a folding-and-inverse-folding pipeline
Developers report: Developers report that a 350M model matches or arguably beats a baseline with 43x more parameters on pseudo-perplexity, with about 17x less training compute and much faster inference, attributing this to data quality.
Independent evidence: No independent evidence found. A row-by-row check of the official board found no entry, and no third-party evaluation was found
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | Three public databases combined into one public dataset: a sequence database, an antibody database and a structural-classification database source |
| b. Private or licensed data | No | No private or licensed data reported |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | No |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: An academic-industry collaboration with no separate company: an AI research institute in Montreal, Canada and a lab at a local engineering university, together with the research arm of a large US biopharma company headquartered in California.
- Funding: The paper does not itemise funding; nothing inferred
- Products and partnerships: Releases 120M and 350M sizes together with the training dataset and is included in a GPU vendor's bio-model framework. Its research question targets the scale-first route represented by ESM3 and ESM C.
- Related models: ESM3, ESM C, SaProt
Reading notes
- Its contribution is methodological; it has no entry on the official zero-shot board and cannot enter board comparisons.
- The "beats the largest baseline" claim is limited to "some tasks" with no public task list or figures.
- Most self-evaluations are own-built or off-site benchmarks, not comparable with the 44 on this site.
- Fully open, dataset included, so it is cheap to reproduce and useful as a control baseline.
Caveats
- Zero pairings: under this round's relation rules it has no established pairing with the 44 site benchmarks.
- The task list behind the claimed advantage is not public and cannot be checked (unverified).
- Licence statements conflict: MIT for the weights, Apache 2.0 elsewhere.
- No wet lab and no third-party evaluation.
Sources
- AMPLIFY preprint (v1 2024-09, v2 2026-01) (preprint)
- Weights and model card (120M) (repository)
- Public training dataset (repository)
- Official repository commit history (repository)
- Institute explainer page with the developer framing (official site)
- Third-party framework documentation (official site)
- Preprint version metadata (archive)
- ProteinGym official summary table, checked row by row with no entry (leaderboard)
Corrections
2 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update.event_kind | Recorded as a new version | Changed to a paper revision: 2026-01-05 is preprint v2, not a new model version, and no journal version exists | source | 2026-11-16 |
| latest_update.description | Said only "v2 revision" plus one code change | Adds the v1 and v2 dates, states there is no journal version and that code changes are minor with the last commit on 2025-07-17 | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.