pubchem-database
>
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
>
>-
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use…
Generate a Reveal.js HTML presentation from Markdown. Use when the user asks to generate a Reveal.js HTML presentation from Markdown.
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling.…
初始化内容创作系统:检查软件依赖是否装齐 + 建好全部目录结构。用户说"初始化内容系统""搭建工作区""建好文件夹""我的文件夹不全""缺什么软件"时使用。依赖缺的给安装命令并按国内镜像帮装,目录建在 AI第二大脑 下,每个目录附一份用途说明 README。
|
Strategic publication planning and venue selection for research
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange interven…
>
Arbitrate conflicting reports into a source-grounded claim audit and reconciled synthesis.
|
UIBC(国际自治之物挑战赛)医疗器械域参赛队。以 TH-MED-001/002/003 判据为底座,参加「迁移的判定与问责」赛题——给定一次记忆迁移,证明「迁移后仍是同一个 Agent」并为判定负责。三层交付:判定规则(L1 有籍)/证据包(L2 有证)/失败处置与责任归属(L3 有门禁),并须声明判据可形式化等级 L0–L4。
Search PubMed, fetch article metadata, traverse citation graphs, and look up MeSH terms from the command line. Use when: (1) Searching PubMed with Boolean/MeSH queries, (2) Fetching article details by…
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you ne…
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 fo…
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of n…
End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private dat…
|
UIBC(国际自治之物挑战赛)自动驾驶域参赛队。以 TH-AUT-001 判据为底座,参加「迁移的判定与问责」赛题——给定一次记忆迁移,证明「迁移后仍是同一个 Agent」并为判定负责。三层交付:判定规则(L1 有籍)/证据包(L2 有证)/失败处置与责任归属(L3 有门禁),并须声明判据可形式化等级 L0–L4。