Readme: fix generation, update transformers version instructions

#121
by pcuenq HF staff - opened
Files changed (1) hide show
  1. README.md +2 -8
README.md CHANGED
@@ -17,13 +17,7 @@ Our model hasn't been fine-tuned through reinforcement learning from human feedb
17
 
18
  ## How to Use
19
 
20
- Phi-2 has been integrated in the development version (4.37.0.dev) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following:
21
-
22
- * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function.
23
-
24
- * Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source.
25
-
26
- The current `transformers` version can be verified with: `pip list | grep transformers`.
27
 
28
  ## Intended Uses
29
 
@@ -103,7 +97,7 @@ inputs = tokenizer('''def print_prime(n):
103
  """''', return_tensors="pt", return_attention_mask=False)
104
 
105
  outputs = model.generate(**inputs, max_length=200)
106
- text = tokenizer.batch_decode(outputs)[0]
107
  print(text)
108
  ```
109
 
 
17
 
18
  ## How to Use
19
 
20
+ Phi-2 was integrated in `transformers` version 4.37. If you need to use an earlier version, you need to pass `trust_remote_code=True` to the `from_pretrained()` function.
 
 
 
 
 
 
21
 
22
  ## Intended Uses
23
 
 
97
  """''', return_tensors="pt", return_attention_mask=False)
98
 
99
  outputs = model.generate(**inputs, max_length=200)
100
+ text = tokenizer.batch_decode(outputs[0])
101
  print(text)
102
  ```
103