a self-trained 0.5B llm in one Nvdia 4090 from zero to one
4
stars
7
commits
Python
primary language
May 27, 2025
updated
py 3.10.8 cuda 11.8 torch 需要从官方下载，pip没有
7 commits
Reset816/LLM-Collection
1
drbaph/NATTEN-0.21.6-torch2100cu130-cp312-cp312-win_amd64
naxneri/natten-0.21.6-blackwell-cu128-cp312-cp312-win_amd64
3
AILab-CVC/seed-llama-14b-pretrain
0
yatoooon/TensorRT-LLM
ylwt/PaddlePaddle-TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
AILab-CVC/seed-llama-8b-pretrain
hjzccc/trtllm
98.8%
