You can deploy this model and start earning money today!

phuctahong/
nanogpt-gpt-mha-falcon-1a-ctxbeta-ctxlambda-chunk-triton-379m-job11173483-step100000

Name: nanogpt-gpt-mha-falcon-1a-ctxbeta-ctxlambda-chunk-triton-379m-job11173483-step100000
Availability: InStock

Views

No views yet

phuctahong/nanogpt-gpt-mha-falcon-1a-ctxbeta-ctxlambda-chunk-triton-379m-job11173483-step100000

NanoGPT Pro checkpoint uploaded from the princeton-pli/Nanogpt W&B project.

Provenance

W&B run: M_gpt-mha-falcon-1A-ctxbeta-ctxlambda-chunk-triton_379m_Opt_adamw_LR_0.001_D_fineweb-edu100B_T_49.15B_time_20260719_130628_jobid_11173483
W&B run id: 46uh18lr
Job id: 11173483
Checkpoint step: 100000
Local checkpoint: /scratch/gpfs/ARORA/st0490/nanogpt-next_mod/output/falcon_1A_ctxbeta_ctxlambda_medium_80g4/out_gpt-mha-falcon-1A-ctxbeta-ctxlambda-chunk-triton_379m_Opt_adamw_LR_0.001_D_fineweb-edu100B_T_49.15B_time_20260719_130628_jobid_11173483/checkpoint-100000

Files

This repo contains inference-ready weights only:

config.json
model.safetensors
generation_config.json

Optimizer and trainer state were intentionally omitted.

Load locally

python

from nanogptpro.model_loader import load_model_from_checkpoint

model = load_model_from_checkpoint(
    model_id="<your-model-id>",
    checkpoint="phuctahong/nanogpt-gpt-mha-falcon-1a-ctxbeta-ctxlambda-chunk-triton-379m-job11173483-step100000",
)

Install nanogptpro and use the model id that matches the architecture recorded in config.json.