Downloads · 30 days
94
0% of all-time downloads
hoskinson-center/proofGPT-v0.1
proofGPT-v0.1 is a text generation model from hoskinson-center. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
ProofGPT-v0.1 is a 1.3B parameter language model based on the GPT-NeoX architecture and trained on the proof-pile (v1.1). We initiailized training with pythia-1.3b weights, a precursor to the pythia-1.4b model that ha…
Downloads · 30 days
94
0% of all-time downloads
All-time downloads
68K
Public
Repo size
8.8 GB
Likes
3
Public
Click a slice to open those files.
.bin2.9 GB · 100%
From the Hugging Face model README
ProofGPT-v0.1 is a 1.3B parameter language model based on the GPT-NeoX architecture and trained on the proof-pile (v1.1). We initiailized training with pythia-1.3b weights, a precursor to the pythia-1.4b model that has roughly equivalent performance.
Detailed evaluations coming soon :)
Note: Commit 3bcdc4e replaced the weights with a model trained on proof-pile v1.1, as opposed to previous commits which were trained on v1.0. Commit 9695b51 updated the tokenizer to have bos, eos, and unk tokens.