Results for “protein-language-models”

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Conjunto abrangente de ferramentas para modelos de linguagem de proteínas, incluindo ESM3 (design multimodal generativo de proteínas em sequência, estrutura e função) e ESM C (embeddings e representações eficientes de proteínas). Use essa skill ao trabalhar com sequências de proteínas, estruturas ou predição de função; designing de proteínas inovadoras; geração de embeddings de proteínas; inverse folding; ou tarefas de engenharia de proteínas. Suporta tanto uso local de modelos quanto Forge API baseada em nuvem para inferência escalável.

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Run ESM protein language models — ESM3 for generative multimodal protein design across sequence, structure, and function, and ESM C for efficient embeddings and representations — locally or via the cloud Forge API. Use when working with protein sequences, structures, or function prediction, designing novel proteins, generating protein embeddings, performing inverse folding, or doing protein-engineering tasks. Part of the AlterLab Academic Skills suite.

Generate, predict, and embed protein sequences and structures using ESM3, ESMC, and ESMFold2 with local or cloud inference.

LoRA: Low-Rank Adaptation of Large Language Models

Scaling Data-Constrained Language Models

Generates and analyzes protein sequences and structures using ESM3, ESMC, and ESMFold2, with support for local and cloud inference.

GLIP: Grounded Language-Image Pre-training

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Scaling Laws for Neural Language Models

Multimodal Few-Shot Learning with Frozen Language Models

Manages the lifecycle of large language models in production, covering model versioning, prompt management, inference optimization, and cost control.

Flamingo: A Visual Language Model for Few-Shot Learning

Scaling Instruction-Finetuned Language Models

Dolphins: Multimodal Language Model for Driving

NLVR2: A Visual Reasoning Benchmark for Natural Language

Large Language Model development, training, fine-tuning, and deployment best practices.

CogVLM: Visual Expert for Pretrained Language Models

Benchmarks large audio-language models against adversarial audio attacks using the CAA dataset, computing WER, ROUGE-L, cosine similarity, and coherence scores to assess robustness in conversational settings.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Build LLM-powered applications with modular components for chains, agents, memory, and retrieval, supporting Python and JavaScript frameworks.

Deduplicating Training Data Makes Language Models Better

Explain and apply core ML/AI concepts — model types, training pipelines, evaluation metrics, and neural architectures.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness

DreamLIP: Language-Image Pre-training with Long Captions

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Analyse the language demands of a classroom task to identify barriers for EAL and multilingual learners. Use when adapting tasks, planning support, or assessing linguistic accessibility.

Build and sharpen a project's domain model — a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Repo decision-memory system (INDEX.md, rejected alternatives) → docs-adr.

Analyze proteomics and metabolomics mass spectrometry data with PyOpenMS: read/write MS file formats, process spectra, detect and quantify features, identify peptides and proteins, and run end-to-end LC-MS/MS pipelines using ready-to-run scripts.