pszemraj/decoder-pytorch-template

Hackable PyTorch template for decoder-only transformer architecture experiments. Llama baseline with RoPE, SwiGLU, RMSNorm. Swap components, train, compare

20
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 1 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

1

Forks

—

Language

Python

License

MIT

Category

llm-quantization-methods

Last pushed

Jan 23, 2026

Commits (30d)

0

GitHub
LLM Quantization Methods · 71 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pszemraj/decoder-pytorch-template"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

intel/auto-round

🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality...

88

ModelCloud/GPTQModel

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD...

86

pytorch/ao

PyTorch native quantization and sparsity for training and inference

74

Picovoice/picollm

On-device LLM Inference Powered by X-Bit Quantization

62

NVIDIA/kvpress

LLM KV cache compression made easy

62

Explore Transformer Models

All categories Trending Transformer directory Insights