kwaikeg
/

kagentlms_baichuan2_13b_mat

Text2Text Generation

feature-extraction

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

myscarlet commited on Dec 11, 2023

Commit

16c1be6

·

1 Parent(s): 6c5f1af

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -26,8 +26,8 @@ Tutorial can refer to [baichuan-inc/Baichuan2-13B-Base](https://github.com/baich
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan2-13B-Base", use_fast=False, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-13B-Base", device_map="auto", trust_remote_code=True)
 inputs = tokenizer('登鹳雀楼->王之涣\n夜雨寄北->', return_tensors='pt')
 inputs = inputs.to('cuda:0')
 pred = model.generate(**inputs, max_new_tokens=64, repetition_penalty=1.1)

 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("kwaikeg/kagentlms_baichuan2_13b_mat", use_fast=False, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("kwaikeg/kagentlms_baichuan2_13b_mat", device_map="auto", trust_remote_code=True)
 inputs = tokenizer('登鹳雀楼->王之涣\n夜雨寄北->', return_tensors='pt')
 inputs = inputs.to('cuda:0')
 pred = model.generate(**inputs, max_new_tokens=64, repetition_penalty=1.1)