Downloads · 30 days
15
6% of all-time downloads
greyscope-v2-qwen3.5-4b-int4
yaoandy107/greyscope-v2-qwen3.5-4b-int4
greyscope-v2-qwen3.5-4b-int4 is a text classification model from yaoandy107. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
This is the 3.5 GB Transformers int4-HQQ build of Greyscope v2. It returns the same continuous aiinvolvement score and human / AI-edited / AI-generated labels as the bf16 model.
All-time downloads
267
Public
Parameters
1.2B
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 99%
Parameter types
How the weights are stored.
BF16700M · 58%
Try a prompt
Base models
Model card
From the Hugging Face model README
Greyscope v2 int4
This is the 3.5 GB Transformers int4-HQQ build of Greyscope v2. It returns the same continuous
ai_involvement score and human / AI-edited / AI-generated labels as the
bf16 model.
Use this build when you need Transformers but cannot fit bf16. Do not use it on Apple Silicon; use MLX 4-bit.
Quick start
git clone https://github.com/yaoandy107/greyscope
cd greyscope
uv sync --extra int4
uv run greyscope --model int4 "Paste a paragraph here."
Quantization check
The release export checked this artifact against bf16 on 64 rows. Treat this as a smoke test, not a quality benchmark, and validate it on your own data and hardware.
Evaluations, calibration, training details, and limitations are documented on the bf16 model card.
- Task
- Text Classification
- Library
- transformers
- Type
- qwen3_5_text
- License
- apache-2.0
- Languages
- en, ja, zh
- Created
- Jul 20, 2026
- Updated
- Jul 28, 2026