gugarosa commited on
Commit
39afec1
1 Parent(s): eb8bbd1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -16,6 +16,16 @@ Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the
16
 
17
  Our model hasn't been fine-tuned through reinforcement learning from human feedback. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
18
 
 
 
 
 
 
 
 
 
 
 
19
  ## Intended Uses
20
 
21
  Given the nature of the training data, the Phi-2 model is best suited for prompts using the QA format, the chat format, and the code format.
 
16
 
17
  Our model hasn't been fine-tuned through reinforcement learning from human feedback. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
18
 
19
+ ## How to Use
20
+
21
+ 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:
22
+
23
+ * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function.
24
+
25
+ * 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.
26
+
27
+ The current `transformers` version can be verified with: `pip list | grep transformers`.
28
+
29
  ## Intended Uses
30
 
31
  Given the nature of the training data, the Phi-2 model is best suited for prompts using the QA format, the chat format, and the code format.