Update README.md
Browse files
README.md
CHANGED
@@ -37,7 +37,7 @@ All models are trained on the full AAID instruction tuning data.
|
|
37 |
|
38 |
## Usage
|
39 |
|
40 |
-
You can use the
|
41 |
|
42 |
```python
|
43 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
@@ -45,7 +45,7 @@ tokenizer = AutoTokenizer.from_pretrained('lzw1008/Emobloom-7b')
|
|
45 |
model = AutoModelForCausalLM.from_pretrained('lzw1008/Emobloom-7b', device_map='auto')
|
46 |
```
|
47 |
|
48 |
-
In this example,
|
49 |
use the GPU if it's available.
|
50 |
|
51 |
## Prompt examples
|
|
|
37 |
|
38 |
## Usage
|
39 |
|
40 |
+
You can use the Emobloom-7b model in your Python project with the Hugging Face Transformers library. Here is a simple example of how to load the model:
|
41 |
|
42 |
```python
|
43 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
45 |
model = AutoModelForCausalLM.from_pretrained('lzw1008/Emobloom-7b', device_map='auto')
|
46 |
```
|
47 |
|
48 |
+
In this example, AutoTokenizer is used to load the tokenizer, and AutoModelForCausalLM is used to load the model. The `device_map='auto'` argument is used to automatically
|
49 |
use the GPU if it's available.
|
50 |
|
51 |
## Prompt examples
|