Downloads · 30 days
15
14% of all-time downloads
neroai14/Nero-Qwen2.5-1.5B-Surgical
Nero-Qwen2.5-1.5B-Surgical is a machine learning model from neroai14. 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.
This model is a surgically optimized version of Qwen2.5-1.5B-Instruct. It was compressed using the Nero Hybrid Engine, an experimental framework designed to reduce VRAM footprint while preserving core logic and reason…
Downloads · 30 days
15
14% of all-time downloads
All-time downloads
104
Public
Parameters
1.5B
3.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors3.1 GB · 100%
From the Hugging Face model README
This model is a surgically optimized version of Qwen2.5-1.5B-Instruct. It was compressed using the Nero Hybrid Engine, an experimental framework designed to reduce VRAM footprint while preserving core logic and reasoning capabilities.
Unlike traditional "blind" quantization, the Nero Engine applies a surgical approach:
self_attn and lm_head are kept at higher precision to ensure the model doesn't lose its "common sense."from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "neroai14/Nero-Qwen2.5-1.5B-Surgical"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
"yassin/Nero-Quantizer",
dtype="auto", # <--- Make sure this says 'dtype', NOT 'torch_dtype'
device_map="auto"
)