PUMA Vault
Search
Buscar
Modo oscuro
Modo claro
Explorador
Etiqueta: training
2 artículos con esta etiqueta.
01 may 2026
RLHF and Constitutional AI — LLM Alignment Training Paradigms
permanent
rlhf
constitutional-ai
rlaif
ppo
reward-model
alignment
ai-safety
fine-tuning
sft
anthropic
openai
puma-core
research
training
ethics
llm
models
hitl
13 abr 2026
Fine-Tuning LLMs — LoRA, QLoRA, GGUF Quantization, and PUMA Considerations
permanent
fine-tuning
lora
qlora
quantization
gguf
ollama
llm
training
puma-core
research
agents
benchmark
local-models
effort-estimation
issue-triage
architecture