Downloads · 30 days
0
SenseNova-U1.5-8B-MoT-LoRAs
xocialize/SenseNova-U1.5-8B-MoT-LoRAs
SenseNova-U1.5-8B-MoT-LoRAs is a machine learning model from xocialize. 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 apache-2.0.
Verbatim mirror of sensenova/SenseNova-U1.5-8B-MoT-LoRAs — the official 8-step distillation LoRAs (0.4B, rank 128, generation-stream only) for SenseNova-U1.5-8B-MoT, by SenseTime / SenseNova. Apache-2.0, mirrored unmo…
Access
Public
Updated Oct 11, 2026
Repo size
1.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 24, 2026
- Updated
- Oct 11, 2026
- SHA
- 1ef89a4d
Base models
Model card
From the Hugging Face model README
SenseNova-U1.5-8B-MoT-LoRAs (durability mirror)
Verbatim mirror of sensenova/SenseNova-U1.5-8B-MoT-LoRAs — the official 8-step distillation LoRAs (0.4B, rank 128, generation-stream only) for SenseNova-U1.5-8B-MoT, by SenseTime / SenseNova. Apache-2.0, mirrored unmodified for supply-chain durability of the sensenova-u1-swift runtime (merge-at-load path). All credit to the SenseNova team — see the upstream card for full documentation.
| file | upstream commit | note |
|---|---|---|
SenseNova-U1.5-8B-MoT-LoRA-8step.safetensors | e909f46 (2026-08-20) | V1 |
SenseNova-U1.5-8B-MoT-LoRA-8step-V2.safetensors | f33b8fe (2026-09-24) | V2 — upstream's recommended adapter: better colour balance, more natural contrast, less oversharpening. Same 882-tensor key set, shapes and alpha as V1. sha256 f4190cabd01fa261a45be853275c483d3a8069295c52cf01f7b2b31f4356f201. |
Prebuilt LoRA-merged MLX artifacts (V1): 8step-8bit · 8step-4bit.
- License
- apache-2.0
- Created
- Aug 24, 2026
- Updated
- Oct 11, 2026