DeepSeek-R1-Distill-Qwen-7B-gptqmodel-4bit-vortex-v2/README.md

base_model, pipeline_tag, tags, license

base_model	pipeline_tag	tags	license
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	text-generation	gptqmodel modelcloud chat qwen deepseek instruct int4 gptq 4bit W4A16	apache-2.0

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：
  • quantizer: gptqmodel:1.7.4
  • uri: https://github.com/modelcloud/gptqmodel
  • damp_percent: 0.1
  • damp_auto_increment: 0.0025

Example:

from transformers import AutoTokenizer
from gptqmodel import GPTQModel

tokenizer = AutoTokenizer.from_pretrained("ModelCloud/DeepSeek-R1-Distill-Qwen-7B-gptqmodel-4bit-vortex-v2")
model = GPTQModel.load("ModelCloud/DeepSeek-R1-Distill-Qwen-7B-gptqmodel-4bit-vortex-v2")

messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You should think step-by-step."},
    {"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)