abhijitgayen
commited on
Commit
·
884fbe1
1
Parent(s):
1a1a0a0
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Trying to make AI conversation
|
2 |
+
|
3 |
+
for this fine-tuning of this model. here we use the **[dataset](abhijitgayen/cogo_chat)**
|
4 |
+
|
5 |
+
# How to use this Model
|
6 |
+
|
7 |
+
```python
|
8 |
+
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
9 |
+
|
10 |
+
model_id= "abhijitgayen/cogo-blenderbot"
|
11 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
12 |
+
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
|
13 |
+
|
14 |
+
UTTERANCE = "help me to book fcl"
|
15 |
+
print("Human: ", UTTERANCE)
|
16 |
+
|
17 |
+
inputs = tokenizer([UTTERANCE], return_tensors="pt")
|
18 |
+
reply_ids = model.generate(**inputs)
|
19 |
+
print("Bot: ", tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0])
|
20 |
+
```
|
21 |
+
|
22 |
+
|
23 |
+
# Out Put
|
24 |
+
|
25 |
+
Response is good but it is take time to give response..As chatbot a real time application. if it takes more than 20 sec , it is meaningless.
|