narinzar's picture
Upload README.md with huggingface_hub
aee274d verified
|
Raw
History Blame Contribute Delete
1.27 kB
metadata
license: mit
library_name: pytorch
tags:
  - char-lm
  - transformer
  - kv-cache
  - educational
datasets:
  - tiny_shakespeare
pipeline_tag: text-generation

tinygpt-shakespeare (kv-cache-throughput-bench)

A 3.307M-parameter char-level decoder-only transformer trained from scratch on Tiny Shakespeare. It exists to drive the benchmarks in the kv-cache-throughput-bench repo: a from-scratch KV cache, a cached-vs-uncached throughput sweep, and an eviction-policy study.

Architecture

  • 4 layers, 4 heads, 256 embedding dim, block size 512, vocab 65 (characters)
  • weight-tied token embeddings, pre-norm blocks, learned absolute positions

Training

  • 2000 steps, batch 48, block 512, AdamW lr 3e-4
  • 134 s on a single RTX 5090 Laptop GPU (CUDA 12.8)
  • final validation loss 1.543, perplexity 4.68

Files

  • tinygpt.pt: state dict plus the config and char->id map

Usage

Clone the repo and load with the provided code:

from src.train import load_model
model, stoi, itos = load_model("tinygpt.pt")

Intended use and limits

Educational. A char model this small produces locally-coherent but repetitive text under greedy decoding. It is not meant for downstream language tasks.