Hugging Face's logo

Intel
/
Qwen2-7B-int4-inc

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
4-bit precision
intel/auto-round
Model card Files Community
1
weiweiz1 commited on
Commit
8ba65eb
·
verified ·
1 Parent(s): fd880bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -26,8 +26,7 @@ from auto_round.auto_quantizer import AutoHfQuantizer
26
  from transformers import AutoModelForCausalLM,AutoTokenizer
27
  quantized_model_dir = "Intel/Qwen2-7B-int4-inc"
28
  tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
29
- model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
30
- tokenizer = AutoTokenizer.from_pretrained(model_name)
31
  text = "下面我来介绍一下阿里巴巴公司，"
32
  text = "88+99等于多少？"
33
  text = "Once upon a time,"
 
26
  from transformers import AutoModelForCausalLM,AutoTokenizer
27
  quantized_model_dir = "Intel/Qwen2-7B-int4-inc"
28
  tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
29
+ model = AutoModelForCausalLM.from_pretrained(quantized_model_dir, device_map="auto")
 
30
  text = "下面我来介绍一下阿里巴巴公司，"
31
  text = "88+99等于多少？"
32
  text = "Once upon a time,"