Update README.md
Browse files
README.md
CHANGED
@@ -14,8 +14,6 @@ datasets:
|
|
14 |
- wikipedia
|
15 |
---
|
16 |
|
17 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
-
should probably proofread and complete it, then remove this comment. -->
|
19 |
|
20 |
# mGPT: fine-tune on message data MWE
|
21 |
|
@@ -23,15 +21,25 @@ This model is a fine-tuned version of [sberbank-ai/mGPT](https://huggingface.co/
|
|
23 |
|
24 |
## Model description
|
25 |
|
26 |
-
|
|
|
27 |
|
28 |
-
|
29 |
|
30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
|
32 |
-
## Training and evaluation data
|
33 |
|
34 |
-
More information needed
|
35 |
|
36 |
## Training procedure
|
37 |
|
|
|
14 |
- wikipedia
|
15 |
---
|
16 |
|
|
|
|
|
17 |
|
18 |
# mGPT: fine-tune on message data MWE
|
19 |
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
24 |
+
- testing if fine-tuned personality data bleeds over to other languages without being trained in them explicitly
|
25 |
+
- for some reason inference API is not pleased with the model but it works fine in Python
|
26 |
|
27 |
+
### Usage in python
|
28 |
|
29 |
+
Install the transformers library if you don't have it:
|
30 |
+
|
31 |
+
pip install -U transformers
|
32 |
+
load the model into a pipeline object:
|
33 |
+
|
34 |
+
from transformers import pipeline
|
35 |
+
import torch
|
36 |
+
device = 'cuda' if torch.cuda.is_available() else 'cpu'
|
37 |
+
my_chatbot = pipeline('text-generation',
|
38 |
+
'pszemraj/mGPT-Peter-mwe',
|
39 |
+
device=0 if device == 'cuda' else -1,
|
40 |
+
)
|
41 |
|
|
|
42 |
|
|
|
43 |
|
44 |
## Training procedure
|
45 |
|