Update README.md
Browse files
README.md
CHANGED
@@ -19,6 +19,16 @@ For a safer model release, we exclude generic web-crawl data sources such as com
|
|
19 |
|
20 |
Phi-1.5 can write poems, draft emails, create stories, summarize texts, write Python code (such as downloading a Hugging Face transformer model), etc.
|
21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
## Intended Uses
|
23 |
|
24 |
Given the nature of the training data, Phi-1.5 is best suited for prompts using the QA format, the chat format, and the code format. Note that Phi-1.5, being a base model, often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.
|
|
|
19 |
|
20 |
Phi-1.5 can write poems, draft emails, create stories, summarize texts, write Python code (such as downloading a Hugging Face transformer model), etc.
|
21 |
|
22 |
+
## How to Use
|
23 |
+
|
24 |
+
Phi-1.5 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:
|
25 |
+
|
26 |
+
* When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function.
|
27 |
+
|
28 |
+
* 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.
|
29 |
+
|
30 |
+
The current `transformers` version can be verified with: `pip list | grep transformers`.
|
31 |
+
|
32 |
## Intended Uses
|
33 |
|
34 |
Given the nature of the training data, Phi-1.5 is best suited for prompts using the QA format, the chat format, and the code format. Note that Phi-1.5, being a base model, often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.
|