🐛 Update: We have discovered a regression in the QwQ Vortext v1 model that may output extra strings such as "Edited Text" that was result of invalid calibration data auto-injected by our vortex pipeline.
Please use v2 of the model here: https://huggingface.co/ModelCloud/QwQ-32B-Preview-gptqmodel-4bit-vortex-v2

image/png

This model has been quantized using GPTQModel.

  • bits: 4
  • dynamic: null
  • group_size: 32
  • desc_act: true
  • static_groups: false
  • sym: true
  • lm_head: false
  • true_sequential: true
  • quant_method: "gptq"
  • checkpoint_format: "gptq"
  • meta

Example:

from transformers import AutoTokenizer
from gptqmodel import GPTQModel

tokenizer = AutoTokenizer.from_pretrained("ModelCloud/QwQ-32B-Preview-gptqmodel-4bit-vortex-v1")
model = GPTQModel.load("ModelCloud/QwQ-32B-Preview-gptqmodel-4bit-vortex-v1")

messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": "How can I design a data structure in C++ to store the top 5 largest integer numbers?"},
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=512)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)

print(result)
Downloads last month
1,146
Safetensors
Model size
6.56B params
Tensor type
BF16
·
I32
·
FP16
·
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for ModelCloud/QwQ-32B-Preview-gptqmodel-4bit-vortex-v1

Base model

Qwen/Qwen2.5-32B
Quantized
(96)
this model

Collection including ModelCloud/QwQ-32B-Preview-gptqmodel-4bit-vortex-v1