P01son commited on
Commit
4e2328a
1 Parent(s): a5e1f26

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -1
README.md CHANGED
@@ -2,4 +2,34 @@
2
  license: apache-2.0
3
  ---
4
 
5
- Training details: https://github.com/CVI-SZU/Linly
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: apache-2.0
3
  ---
4
 
5
+ Training details: https://github.com/CVI-SZU/Linly
6
+
7
+
8
+ ```python
9
+ from transformers import AutoTokenizer, AutoModelForCausalLM
10
+ import transformers
11
+ import torch
12
+
13
+ model = "Linly-AI/Chinese-Falcon-7B"
14
+
15
+ tokenizer = AutoTokenizer.from_pretrained(model)
16
+ pipeline = transformers.pipeline(
17
+ "text-generation",
18
+ model=model,
19
+ tokenizer=tokenizer,
20
+ torch_dtype=torch.bfloat16,
21
+ trust_remote_code=True,
22
+ device_map="auto",
23
+ )
24
+ sequences = pipeline(
25
+ "User: 你如何看待996?\nBot: 我认为996制度是一种不可取的工作时间安排,因为这会导致员工过多的劳累和身心健康问题。此外,如果公司想要提高生产效率,应该采用更有效的管理方式,而不是通过强行加大工作量来达到目的。\nUser: 那么你有什么建议?\nBot:",
26
+ max_length=200,
27
+ do_sample=True,
28
+ top_k=10,
29
+ num_return_sequences=1,
30
+ eos_token_id=tokenizer.eos_token_id,
31
+ )
32
+ for seq in sequences:
33
+ print(f"Result: {seq['generated_text']}")
34
+
35
+ ```