Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
ChrisMcCormick
/
decoderstack-d24
Like
0
English
decoderstack
nanochat
pretraining
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
47b3fec
decoderstack-d24
40.4 GB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
ChrisMcCormick
tokenizer: regenerate token_bytes.pt with upstream 2ce972a raw-bytes fix (191/32768 ids corrected)
47b3fec
verified
about 2 months ago
base_checkpoints
meta_005568.json: add user_config so chat_sft inherits the run's LRs
about 2 months ago
checkpoints
Upload folder using huggingface_hub
about 2 months ago
code
Add model card, meta.json, logs, tokenizer, training source, and nanochat converter
about 2 months ago
logs
Add model card, meta.json, logs, tokenizer, training source, and nanochat converter
about 2 months ago
tokenizer
tokenizer: regenerate token_bytes.pt with upstream 2ce972a raw-bytes fix (191/32768 ids corrected)
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
about 2 months ago
README.md
13.9 kB
Model card: step 5568 is now a ready-made nanochat checkpoint (+8-rank optimizer shards)
about 2 months ago
convert_ckpt_to_nanochat.py
Safe
26.3 kB
Converter now emits nanochat optimizer shards for an SFT warm-start
about 2 months ago
test_convert_ckpt_to_nanochat.py
Safe
13.9 kB
Converter now emits nanochat optimizer shards for an SFT warm-start
about 2 months ago