Andreas Trawoeger avatar

Andreas Trawoeger

Community

@atrawog · Vienna,Austria

40Followers
|
110Public Repos
|
42Published Skills

Agent Skills by Andreas Trawoeger

Showing 42 vetted skills indexed across 1 GitHub repositories.

atrawogatrawog

gpu

Monitor GPU status, VRAM, and loaded models for Ollama inference.

Community
Intermediate
atrawogatrawog

chat

Access Ollama REST API endpoints from Python for model management.

Community
Intermediate
atrawogatrawog

langchain

Automate LLM application development with prompts, models, and orchestration abstractions.

Community
Advanced
atrawogatrawog

qlora

Fine-tune large language models with QLoRA adapters and configurable quantization.

Community
Advanced
atrawogatrawog

vision

Fine-tune vision-language models with Unsloth's FastVisionModel and LoRA.

Community
Advanced
atrawogatrawog

finetuning

Fine-tune domain-specific LLMs with PyTorch and HuggingFace Trainer.

Community
Advanced
atrawogatrawog

dpo

Optimize policy directly from chosen/rejected preference pairs using DPOTrainer and DPOConfig.

Community
Advanced
atrawogatrawog

rag

Retrieve knowledge base context to ground LLM answers with RAG.

Community
Advanced
atrawogatrawog

peft

Fine-tune large language models with LoRA, QLoRA, Unsloth adapters in PyTorch workflows.

Community
Advanced
atrawogatrawog

quantization

Quantize neural network models to FP32, FP16, BF16, INT8, or INT4 precisions.

Community
Advanced
atrawogatrawog

transformers

Explain Transformer architecture fundamentals including self-attention and building blocks.

Community
Intermediate
atrawogatrawog

grpo

Train models with group-relative policy gradient reinforcement learning.

Community
Advanced
atrawogatrawog

reward

Train reward models with TRL RewardTrainer and LoRA for RLHF pipelines.

Community
Advanced
atrawogatrawog

inference

Run batch and interactive LLM inference with a vLLM backend.

Community
Advanced
atrawogatrawog

evaluation

Evaluate LLM outputs with Evidently.ai descriptors for classification and generative tasks.

Community
Advanced
atrawogatrawog

sft

Provides SFT training patterns and Unsloth optimizations for LLM instruction-tuning workflows.

Community
Advanced
atrawogatrawog

huggingface

Import GGUF models from HuggingFace into Ollama for local inference.

Community
Intermediate
atrawogatrawog

ollama

Manage and interact with local Ollama models via a Pythonic API.

Community
Intermediate
atrawogatrawog

rloo

Reduce gradient variance in reinforcement learning policy optimization with leave-one-out baselines.

Community
Advanced
atrawogatrawog

openai

Migrate OpenAI-based apps to a local Ollama instance via the OpenAI Python client.

Community
Intermediate
atrawogatrawog

openwebui

Configure, start, and monitor Open WebUI for Ollama models.

Community
Advanced
atrawogatrawog

install

Automate installation of standalone development tools via a single dispatcher.

Community
Intermediate
atrawogatrawog

k3d

Manage local k3d Kubernetes clusters inside Podman containers.

Community
Intermediate
atrawogatrawog

record

Record terminal sessions as asciinema cast files with metadata.

Community
Intermediate