Hugging Face's logo

jiangchengchengNLP
/
huatuo_AutoGPTQ_7B4bits

Safetensors
baichuan
custom_code
4-bit precision
gptq
Model card Files Community
jiangchengchengNLP commited on
Commit
f69efda
•
1 Parent(s): b73519a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -28,7 +28,7 @@ cd AutoGPTQ
28
  ```
29
 
30
  ```
31
- from transformers import AutoTokenizer
32
  from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
33
  model = AutoGPTQForCausalLM.from_quantized("jiangchengchengNLP/huatuo_AutoGPTQ_7B4bits", device="cuda:0",trust_remote_code=True)
34
  tokenizer = AutoTokenizer.from_pretrained("jiangchengchengNLP/huatuo_AutoGPTQ_7B4bits",trust_remote_code=True)
 
28
  ```
29
 
30
  ```
31
+ from transformers import AutoTokenizer,TextGenerationPipeline
32
  from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
33
  model = AutoGPTQForCausalLM.from_quantized("jiangchengchengNLP/huatuo_AutoGPTQ_7B4bits", device="cuda:0",trust_remote_code=True)
34
  tokenizer = AutoTokenizer.from_pretrained("jiangchengchengNLP/huatuo_AutoGPTQ_7B4bits",trust_remote_code=True)