数据科学家

Mathematical Science Occupations

数据科学家(Mathematical Science Occupations)相关 AI Agent 技能。支持 Claude Code / Cursor 一键安装。

⭐ 该职业下的热门技能

model-usage.md ★ 377.8k
from "openclaw"
Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.
查看详情 →
slime-rl-training.md ★ 187.8k
from "NousResearch"
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation work
查看详情 →
serving-llms-vllm.md ★ 187.8k
from "NousResearch"
vLLM: high-throughput LLM serving, OpenAI API, quantization.
查看详情 →
jupyter-live-kernel.md ★ 187.8k
from "NousResearch"
Iterative Python via live Jupyter kernel (hamelnb).
查看详情 →
huggingface-hub.md ★ 187.8k
from "NousResearch"
HuggingFace hf CLI: search/download/upload models, datasets.
查看详情 →
sparse-autoencoder-training.md ★ 187.8k
from "NousResearch"
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use w
查看详情 →
huggingface-accelerate.md ★ 187.8k
from "NousResearch"
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device place
查看详情 →
clip.md ★ 187.8k
from "NousResearch"
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-tex
查看详情 →
faiss.md ★ 187.8k
from "NousResearch"
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Fla
查看详情 →
optimizing-attention-flash.md ★ 187.8k
from "NousResearch"
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>
查看详情 →
whisper.md ★ 187.8k
from "NousResearch"
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes fr
查看详情 →
huggingface-tokenizers.md ★ 187.8k
from "NousResearch"
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms.
查看详情 →
llava.md ★ 187.8k
from "NousResearch"
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language mo
查看详情 →
nemo-curator.md ★ 187.8k
from "NousResearch"
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics),
查看详情 →
peft-fine-tuning.md ★ 187.8k
from "NousResearch"
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need t
查看详情 →
© 2026 skillsABC.com — 14.8万+ AI Agent 技能集市
职业分类 数据洞察 提交技能 隐私声明