Agent Skills by mesferali
Showing 90 vetted skills indexed across 1 GitHub repositories.
MesferAlidspy
Program large language models declaratively with signatures and automatic prompt optimization.
MesferAliopenrlhf-training
Train LLMs with PPO, GRPO, RLOO, and DPO using Ray and vLLM.
MesferAlinemo-guardrails
Implement NeMo Guardrails with Colang 2.0 for LLM safety and security.
MesferAlillamaindex
Provides a data framework for building LLM apps with retrieval-augmented generation (RAG) and document ingestion from over 300 sources.
MesferAlideepspeed
Configure DeepSpeed ZeRO stages and pipeline parallelism for distributed AI model training.
MesferAlicrewai-multi-agent
Orchestrate role-based AI agents with sequential or hierarchical workflows.
MesferAlimoe-training
Train Mixture of Experts models using DeepSpeed and HuggingFace Transformers.
MesferAlidrizzle-schema
Define PostgreSQL database schemas with Drizzle ORM and Zod validation.
MesferAlinnsight-remote-interpretability
Run remote mechanistic interpretability experiments on PyTorch models via nnsight and NDIF.
MesferAlilangsmith-observability
Trace, evaluate, and monitor LLM applications with LangSmith observability.
MesferAliaudiocraft-audio-generation
Generate music and sound effects from text using AudioCraft.
MesferAlinemo-curator
Accelerate LLM training data curation with GPU-intensive operations for text, image, video, and audio.
MesferAlihuggingface-accelerate
Simplify distributed training for PyTorch scripts with a unified API.
MesferAliml-paper-writing
Draft ML and AI papers with verified citations for conference submissions.
MesferAlichroma
Store embeddings and perform semantic searches with metadata filtering.
MesferAliprompt-guard
Detect prompt injections and jailbreak attempts in LLM applications.
MesferAlievaluating-llms-harness
Evaluate LLMs across 60+ academic benchmarks using lm-evaluation-harness.
MesferAlillama-factory
Fine-tune large language models with LLaMA-Factory using no-code WebUI and QLoRA.
MesferAliknowledge-distillation
Compress large language models into smaller student models using knowledge distillation.
MesferAlimideast-fintech-content
Generate localized AI, Fintech, and ERP content for Middle East and GCC markets.
MesferAlisimpo-training
Implement SimPO training for LLM alignment using PyTorch and Transformers.
MesferAlislime-rl-training
Train GLM models with RL using Megatron-LM and SGLang.
MesferAliblip-2-vision-language
Generate image captions and answer visual questions with BLIP-2.
MesferAlipytorch-fsdp2
Implement PyTorch FSDP2 distributed training with DTensor sharding and checkpointing.