← Todos los skills

emerging-techniques-long-context

ComunidadMIT

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

El ZIP contiene solo este skill. Está en GitHub Releases del repo público orlandoneto/agent-skills — Ontoom es la vitrina. El crawler diario actualiza el catálogo.

Cómo instalar

  1. Descarga el ZIP y extrae la carpeta del skill.
  2. Cursor: .agents/skills/aitmpl-emerging-techniques-long-context/ o .cursor/skills/aitmpl-emerging-techniques-long-context/
  3. Claude Code: .claude/skills/aitmpl-emerging-techniques-long-context/
  4. Otras IAs: .agents/skills/aitmpl-emerging-techniques-long-context/
cursorclaude-codecodexgeminiany

Otros skills de esta colección

Otras colecciones

  • emerging-techniques-model-merging

    Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

  • emerging-techniques-model-pruning

    Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

  • emerging-techniques-moe-training

    Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

  • emerging-techniques-speculative-decoding

    Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

  • endpoint-validator

    Deterministic API endpoint validation with pass/fail reporting.

  • evaluation-bigcode-evaluation-harness

    Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.