Downloads · 30 days
14
41% of all-time downloads
Llama-3.2-1B-Instruct-safetyquant-c1
Jeesup/Llama-3.2-1B-Instruct-safetyquant-c1
Llama-3.2-1B-Instruct-safetyquant-c1 is a machine learning model from Jeesup. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Quantized variant used in the Safety-Aware Configuration-Conditioned LoRA study.
All-time downloads
34
Public
Parameters
1.5B
2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2 GB · 99%
Parameter types
How the weights are stored.
I8973M · 65%
Base models
Model card
From the Hugging Face model README
Llama-3.2-1B-Instruct — configuration c1 (W8A8)
Quantized variant used in the Safety-Aware Configuration-Conditioned LoRA study.
| field | value |
|---|---|
| scheme | W8A8 |
| method | smoothquant+gptq |
| simulated | no — native kernel |
| weight bits | 8 |
| activation bits | 8 |
| group / block size | None |
| symmetric | True |
| calibration | 512 × 2048 tok, C4 |
| calibration sha256 | b5736155d5b24bf5eb15faae0eb4a742aea4a9d0532db9684085a49750606e19 |
The calibration set is byte-identical across every configuration so that calibration data cannot be confounded with quantization method. c2 vs c3 isolates method (GPTQ vs AWQ) at equal bit-width, and is the study's headline control: 0.0276 vs 0.0661 pooled ASR with non-overlapping 95% CIs.
Metrics, per-prompt judge verdicts and the full report: Jeesup/safety-quant-phase0.
- Type
- llama
- Created
- Aug 9, 2026
- Updated
- Aug 10, 2026