Downloads · 30 days
26
38% of all-time downloads
phuctahong/nanogpt-gpt-mha-delta-net-chunk-triton-fla-379m-job11311678-step100000
nanogpt-gpt-mha-delta-net-chunk-triton-fla-379m-job11311678-step100000 is a machine learning model from phuctahong. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
NanoGPT Pro checkpoint uploaded from the princeton-pli/Nanogpt W&B project.
Downloads · 30 days
26
38% of all-time downloads
All-time downloads
69
Public
Parameters
379M
1.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.5 GB · 100%
From the Hugging Face model README
NanoGPT Pro checkpoint uploaded from the princeton-pli/Nanogpt W&B project.
32dwgtvo11311678100000/scratch/gpfs/JHACKL/nanogpt-next_mod/output/delta_net_medium_80g4_bs20/out_gpt-mha-delta_net_chunk_triton_fla_379m_Opt_adamw_LR_0.001_D_fineweb-edu100B_T_49.15B_time_20260718_142219_jobid_11311678/checkpoint-100000This repo contains inference-ready weights only:
config.jsonmodel.safetensorsgeneration_config.jsonOptimizer and trainer state were intentionally omitted.
from nanogptpro.model_loader import load_model_from_checkpoint
model = load_model_from_checkpoint(
model_id="<your-model-id>",
checkpoint="phuctahong/nanogpt-gpt-mha-delta-net-chunk-triton-fla-379m-job11311678-step100000",
)
Install nanogptpro and use the model id that matches the architecture recorded in
config.json.