Downloads · 30 days
76
16% of all-time downloads
ProCreations/boopit-1
boopit-1 is a text generation model from ProCreations. Use it when you need the model to write or continue text. It is set up for pytorch. The card lists the license as apache-2.0.
This model was asked to be published under my account, not the creators. The compute came from https://huggingface.co/posts/ProCreations/855858308074329
Downloads · 30 days
76
16% of all-time downloads
All-time downloads
489
Public
Repo size
16.4 MB
Likes
1
Public
Click a slice to open those files.
.boopit5.5 MB · 94%
From the Hugging Face model README
This model was asked to be published under my account, not the creators. The compute came from https://huggingface.co/posts/ProCreations/855858308074329
A 27.3M-parameter language model with a 4096 context window and native BitNet b1.58 ternary weights (weights in {-1, 0, 1} from step 0).
This release contains the best held-out-loss checkpoint from pretraining on openbmb/Ultra-FineWeb-L1:
Training continued beyond this checkpoint, but later checkpoints did not improve held-out loss, so this best checkpoint was preserved and selected for release. The packed weights (model.boopit) are under 7 MB.
Architecture: 6 layers, width 512, 8 attention heads, tied embeddings, RMSNorm, GELU MLP, and a byte-level 16,384-token BPE vocabulary.
Chat fine-tune: ProCreations/boopit-1-chat.