MCP App StoreMCP App Store
from argentos-core114
Comprehensive guide for fine-tuning LLMs using TRL, covering SFT, DPO, PPO, and GRPO for human preference alignment.
This skill provides a complete framework for post-training language models to align them with human preferences. It enables the agent to implement complex ML pipelines including Supervised Fine-Tuning (SFT) for instruction following and various reinforcement learning techniques for optimization.
Use this skill when you need to perform RLHF (Reinforcement Learning from Human Feedback), align a model with a preference dataset (chosen vs rejected pairs), or optimize a model using reward functions.
basic_grpo_training.py.Designed for agents with Python execution capabilities and access to NVIDIA GPUs (CUDA), specifically those integrating with HuggingFace Transformers and the TRL library.
This skill has not been reviewed by our automated audit pipeline yet.
Seq Wrangler
Sequence data QC, trimming, alignment, and BAM processing pipeline helper — wraps FastQC, fastp/Trimmomatic, BWA/Bowtie2/Minimap2, and SAMtools for automated re
DSPy — Declarative LM Programming
Use DSPy to build declarative, modular LM pipelines, optimize prompts automatically, and assemble reliable RAG/agent systems with structured signatures and opti
Terradev — Cross‑Cloud GPU Provisioning
Provision and manage GPUs across clouds, create GPU Kubernetes clusters, deploy inference endpoints, and burst local compute to cloud with BYOAPI credential saf
libagent
Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a
Model Deployment (SageMaker & Bedrock)
Generates deployment code and a Jupyter notebook to deploy LoRA fine-tuned Nova or OSS models (from SageMaker Serverless Model Customization) to SageMaker endpo
RAG Implementation Patterns
Practical guide to building production Retrieval-Augmented Generation (RAG) systems: vector DB selection, chunking strategies, embedding model choices, retrieva
Hugging Face Evaluation Manager
Extract, import, and add structured model evaluation results to Hugging Face model cards; run or import benchmark evaluations and generate model-index YAML for
MindsDB
Integrate and interact with MindsDB via the Membrane CLI: manage connections, list and run actions, and automate model predictions against your database.