Downloads · 30 days
263
9% of all-time downloads
SipsaLabs/smollm2-1.7b-uc-v3-bpw3
smollm2-1.7b-uc-v3-bpw3 is a machine learning model from SipsaLabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
UltraCompress is retired. Its public materials preserve historical research; new API access and paid pilots are no longer offered. Results below apply to their recorded evaluation conditions.
Downloads · 30 days
263
9% of all-time downloads
All-time downloads
2.8K
Public
Parameters
1.7B
4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.4 GB · 86%
From the Hugging Face model README
UltraCompress is retired. Its public materials preserve historical research; new API access and paid pilots are no longer offered. Results below apply to their recorded evaluation conditions.
The public v0.6.27 CLI checks basic pack structure and computes SHA-256 fingerprints unless hashing is skipped. It does not reconstruct weights, reproduce the evaluations below, or automatically compare its fingerprint with a trusted reference.
3-bit compression (lossy; larger perplexity drift than the 5-bit line — see verified ratio below) of HuggingFaceTB/SmolLM2-1.7B — produced by Sipsa Labs (UltraCompress).
pip install ultracompress
Documentation & verification: https://sipsalabs.com · https://github.com/sipsalabs/ultracompress
Patents pending.