github
/
InternLM
mirror of https://github.com/InternLM/InternLM
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #7 from 00INDEX/main 

Update: Readme
pull/9/head
Xingcheng Zhang 2023-07-06 16:50:25 +08:00 committed by GitHub
parent ce02dcf54f f01a2832b8
commit 3d6be8826b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README-zh-Hans.md
View File

@ -76,7 +76,7 @@ InternLM ，即书生·浦语大模型，包含面向实用场景的70亿参数
```python ```python
>>> from transformers import AutoTokenizer, AutoModelForCausalLM >>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True) >>> tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
>>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True, device='cuda') >>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).cuda()
>>> model = model.eval() >>> model = model.eval()
>>> response, history = model.chat(tokenizer, "你好", history=[]) >>> response, history = model.chat(tokenizer, "你好", history=[])
>>> print(response) >>> print(response)
@ -137,7 +137,7 @@ python convert2hf.py --src_folder origin_ckpt/ --tgt_folder hf_ckpt/ --tokenizer
转换之后可以通过以下的代码加载为 transformers 转换之后可以通过以下的代码加载为 transformers
```python ```python
>>> from transformers import AutoTokenizer, AutoModel >>> from transformers import AutoTokenizer, AutoModel
>>> model = AutoModel.from_pretrained("hf_ckpt/", trust_remote_code=True, device='cuda') >>> model = AutoModel.from_pretrained("hf_ckpt/", trust_remote_code=True).cuda()
``` ```

2
README.md
View File

@ -144,7 +144,7 @@ python convert2hf.py --src_folder origin_ckpt/ --tgt_folder hf_ckpt/ --tokenizer
After conversion, it can be loaded as transformers by the following code After conversion, it can be loaded as transformers by the following code
```python ```python
>>> from transformers import AutoTokenizer, AutoModel >>> from transformers import AutoTokenizer, AutoModel
>>> model = AutoModel.from_pretrained("hf_ckpt/", trust_remote_code=True, device='cuda') >>> model = AutoModel.from_pretrained("hf_ckpt/", trust_remote_code=True).cuda()
``` ```