gugarosa commited on
Commit
467adac
1 Parent(s): 474b29e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -9
README.md CHANGED
@@ -20,11 +20,7 @@ Phi-1.5 can write poems, draft emails, create stories, summarize texts, write Py
20
 
21
  ## How to Use
22
 
23
- Phi-1.5 has been integrated in the `transformers` version 4.37.0. If you are using a lower version, ensure that you are doing the following:
24
-
25
- * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function.
26
-
27
- The current `transformers` version can be verified with: `pip list | grep transformers`.
28
 
29
  ## Intended Uses
30
 
@@ -91,8 +87,6 @@ where the model generates the text after the comments.
91
 
92
  * Phi-1.5 has not been tested to ensure that it performs adequately for any production-level application. Please refer to the limitation sections of this document for more details.
93
 
94
- * If you are using `transformers<4.37.0`, always load the model with `trust_remote_code=True` to prevent side-effects.
95
-
96
  ## Sample Code
97
 
98
  ```python
@@ -101,8 +95,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
101
 
102
  torch.set_default_device("cuda")
103
 
104
- model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1_5", torch_dtype="auto", trust_remote_code=True)
105
- tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5", trust_remote_code=True)
106
 
107
  inputs = tokenizer('''def print_prime(n):
108
  """
 
20
 
21
  ## How to Use
22
 
23
+ Phi-1.5 has been integrated in the `transformers` version 4.37.0, please ensure that you are using a version equal or higher than it.
 
 
 
 
24
 
25
  ## Intended Uses
26
 
 
87
 
88
  * Phi-1.5 has not been tested to ensure that it performs adequately for any production-level application. Please refer to the limitation sections of this document for more details.
89
 
 
 
90
  ## Sample Code
91
 
92
  ```python
 
95
 
96
  torch.set_default_device("cuda")
97
 
98
+ model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1_5", torch_dtype="auto")
99
+ tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5")
100
 
101
  inputs = tokenizer('''def print_prime(n):
102
  """