You can deploy this model and start earning money today!

phuctahong/
nanogpt-falcon-1-3-lambda-init-0-01-0-01-lambda-scale-0-95-beta-scale-by-2-job5853559-step100000

Name: nanogpt-falcon-1-3-lambda-init-0-01-0-01-lambda-scale-0-95-beta-scale-by-2-job5853559-step100000
Availability: InStock

Views

No views yet

phuctahong/nanogpt-falcon-1-3-lambda-init-0-01-0-01-lambda-scale-0-95-beta-scale-by-2-job5853559-step100000

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

Provenance

W&B run: [[Falcon-1.3-lambda_init-0.01-0.01-lambda_scale-0.95-beta_scale_by_2-false]]M_gpt-mha-scaled_delta_net_parallel_ctxeta_ctxlambda_triton_130m_Opt_adamw_LR_0.001_D_fineweb-edu100B_T_49.15B_time_20260326_124947_jobid_5853559](https://wandb.ai/princeton-pli/Nanogpt/runs/stjxp3tq)
W&B run id: stjxp3tq
Job id: 5853559
Checkpoint step: 100000
Local checkpoint: /scratch/gpfs/ARORA/st0490/nanogpt-next_mod/output/out_gpt-mha-scaled_delta_net_parallel_ctxeta_ctxlambda_triton_130m_Opt_adamw_LR_0.001_D_fineweb-edu100B_T_49.15B_time_20260326_124947_jobid_5853559/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-falcon-1-3-lambda-init-0-01-0-01-lambda-scale-0-95-beta-scale-by-2-job5853559-step100000",
)

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