ChrisMcCormick/nanochat-varlen-d12-2026-03-21

nanochat-varlen-d12

nanochat d12 trained with batch size 32, FP8, and flashattention_varlen. Ran on 1xH100, see run log for results.

Download

import os
from huggingface_hub import hf_hub_download

repo_id = "ChrisMcCormick/nanochat-varlen-d12-2026-03-21"
cache_dir = os.path.expanduser("~/.cache/nanochat")

# Download model checkpoint
hf_hub_download(
    repo_id=repo_id,
    filename="base_checkpoints/d12_speedrun/model_001680.pt",
    local_dir=cache_dir,
)

# Download tokenizer files
hf_hub_download(
    repo_id=repo_id,
    filename="tokenizer/token_bytes.pt",
    local_dir=cache_dir,
)
hf_hub_download(
    repo_id=repo_id,
    filename="tokenizer/tokenizer.pkl",
    local_dir=cache_dir,
)

# Download run log
hf_hub_download(
    repo_id=repo_id,
    filename="logs/d12_speedrun_20260322_001042.log",
    local_dir=cache_dir,
)