Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
language: en
|
4 |
+
tags:
|
5 |
+
- zephyr
|
6 |
+
- conversational
|
7 |
+
license: mit
|
8 |
+
---
|
9 |
+
|
10 |
+
# Zephyr AI Boyfriend
|
11 |
+
|
12 |
+
This is a fine-tuned version of Zephyr, optimized for romantic and friendly conversations.
|
13 |
+
|
14 |
+
## Usage
|
15 |
+
|
16 |
+
```python
|
17 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
18 |
+
|
19 |
+
model = AutoModelForCausalLM.from_pretrained("Ozzai/zephyr-bae")
|
20 |
+
tokenizer = AutoTokenizer.from_pretrained("Ozzai/zephyr-bae")
|
21 |
+
|
22 |
+
# Example usage
|
23 |
+
input_text = "Hey Zephyr, what's on your mind?"
|
24 |
+
inputs = tokenizer(input_text, return_tensors="pt")
|
25 |
+
outputs = model.generate(**inputs, max_new_tokens=100)
|
26 |
+
response = tokenizer.decode(outputs[0])
|
27 |
+
print(response)
|
28 |
+
```
|
29 |
+
|
30 |
+
Enjoy chatting with Zephyr!
|