LisaMegaWatts
/

SymbioGPT-10M

multi-organelle

Model card Files Files and versions

1.49 GB

1 contributor

History: 13 commits

LisaMegaWatts's picture

Add BPE tokenizer (needed for Colab training notebooks)

215b74b verified 11 days ago

data
Add 2MB val text sample for Gemma/HF tokenizer notebooks 14 days ago
distill_test
Distillation test winner (scratch, PPL=43.9, 5M params) 15 days ago
.gitattributes

1.59 kB

Add 20MB raw text sample for Gemma/HF tokenizer notebooks 14 days ago
README.md

1.67 kB

Upload README.md with huggingface_hub 15 days ago
merges.txt

13.8 kB

Upload merges.txt with huggingface_hub 15 days ago
symbio_best.pt
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage"
What is a pickle import?
46.4 MB
xet

Upload best checkpoint (val_loss=3.5599) 15 days ago
symbio_final.pt
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage"
What is a pickle import?
46.4 MB
xet

Upload SymbioGPT-10M teacher (val_ppl=35.3, 13400 steps, A100) 15 days ago
symbio_model.py

29.1 kB

Add symbio_model.py for Colab notebook imports 14 days ago
transformer_tokenizer.py

5.22 kB

Add BPE tokenizer (needed for Colab training notebooks) 11 days ago
vocab.json

33.6 kB

Upload vocab.json with huggingface_hub 15 days ago