Downloads · 30 days
14
23% of all-time downloads
kinkinkin123456/nexus-qwen35-0p8b-smoke-merged
nexus-qwen35-0p8b-smoke-merged is a feature extraction model from kinkinkin123456. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
This repository contains a standalone merged checkpoint produced from the Nexus Qwen3.5-0.8B smoke LoRA adapter.
Downloads · 30 days
14
23% of all-time downloads
All-time downloads
61
Public
Parameters
853M
1.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.7 GB · 99%
From the Hugging Face model README
This repository contains a standalone merged checkpoint produced from the Nexus Qwen3.5-0.8B smoke LoRA adapter.
It is intended for teammates who want a full model directory instead of loading a separate PEFT adapter.
This is a merged full-weight checkpoint.
Main files:
model.safetensorsconfig.jsonprocessor_config.jsontokenizer.jsontokenizer_config.jsonchat_template.jinjanexus_configs/Qwen/Qwen3.5-0.8B10bf16Inside the Nexus codebase, point both model and processor to this directory:
from Nexus import MultimodalEmbedder
model = MultimodalEmbedder(
model_name_or_path="path/to/this/merged/repo",
processor_name_or_path="path/to/this/merged/repo",
model_type="qwen3_5",
trust_remote_code=True,
normalize_embeddings=True,
pooling_method="last_token",
)