Downloads · 30 days
0
alm-add-qwen-non
binhquoc/alm-add-qwen-non
alm-add-qwen-non is a machine learning model from binhquoc. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Access
Public
Updated Dec 28, 2025
Repo size
82.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors82.9 MB · 100%
At a glance
- Access
- Public
- Created
- Dec 28, 2025
- Updated
- Dec 28, 2025
- SHA
- 56a6b538
Model card
From the Hugging Face model README
import torch
from peft import PeftModel
from transformers import AutoProcessor, AutoModelForCausalLM, BitsAndBytesConfig, Qwen2AudioForConditionalGeneration
model_id = "Qwen/Qwen2-Audio-7B-Instruct"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16
)
base_model = Qwen2AudioForConditionalGeneration.from_pretrained(model_id,
device_map="auto",
torch_dtype=torch.bfloat16,
quantization_config=bnb_config,
cache_dir = os.getenv('CACHE_DIR'))
model = PeftModel.from_pretrained(base_model, "binhquoc/alm-add-qwen-non")
processor = AutoProcessor.from_pretrained(model_id, cache_dir = os.getenv('CACHE_DIR'))
- Created
- Dec 28, 2025
- Updated
- Dec 28, 2025