Update README.md
Browse files
README.md
CHANGED
@@ -71,11 +71,29 @@ These results indicate that the model performs reasonably well at identifying th
|
|
71 |
|
72 |
## How to Use
|
73 |
|
74 |
-
|
|
|
|
|
|
|
|
|
75 |
|
76 |
```python
|
77 |
from transformers import pipeline
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
|
79 |
-
classifier = pipeline(
|
80 |
-
|
81 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
## How to Use
|
73 |
|
74 |
+
### Via the Huggingface Space
|
75 |
+
The easiest way to test and try out the model is via its' [Huggingface Space](https://huggingface.co/spaces/abullard1/steam-review-constructiveness-classifier).
|
76 |
+
|
77 |
+
### Via the HF Transformers Library
|
78 |
+
You can also use this model through the Hugging Face transformers `pipeline` API for easy classification. Here's how to do it in Python:
|
79 |
|
80 |
```python
|
81 |
from transformers import pipeline
|
82 |
+
import torch
|
83 |
+
|
84 |
+
device = 0 if torch.cuda.is_available() else -1
|
85 |
+
torch_d_type = torch.float16 if torch.cuda.is_available() else torch.float32
|
86 |
+
|
87 |
+
base_model_name = "albert-base-v2"
|
88 |
+
|
89 |
+
finetuned_model_name = "abullard1/albert-v2-steam-review-constructiveness-classifier"
|
90 |
|
91 |
+
classifier = pipeline(
|
92 |
+
task="text-classification",
|
93 |
+
model=finetuned_model_name,
|
94 |
+
tokenizer=base_model_name,
|
95 |
+
device=device,
|
96 |
+
top_k=None,
|
97 |
+
truncation=True,
|
98 |
+
max_length=512,
|
99 |
+
torch_dtype=torch_d_type)
|