Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,31 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# 🌈 wrapbow.ai — Creative Ad Copy LLM (Based on Mistral 7B)
|
2 |
+
|
3 |
+
`wrapbow.ai` is a domain-tuned version of Mistral 7B Instruct, customized for use cases in:
|
4 |
+
- 🪄 Creative ad banner copywriting
|
5 |
+
- 📢 Promotional messaging
|
6 |
+
- 🧠Prompt-driven content generation for digital ads
|
7 |
+
|
8 |
+
---
|
9 |
+
|
10 |
+
## ✅ Base Model
|
11 |
+
- [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
|
12 |
+
|
13 |
+
---
|
14 |
+
|
15 |
+
## 💡 Example Usage
|
16 |
+
|
17 |
+
```python
|
18 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
19 |
+
|
20 |
+
tokenizer = AutoTokenizer.from_pretrained("ashishkummar/wrapbow.ai", trust_remote_code=True)
|
21 |
+
model = AutoModelForCausalLM.from_pretrained("ashishkummar/wrapbow.ai", trust_remote_code=True)
|
22 |
+
|
23 |
+
prompt = "Generate a banner line for 50% discount on women's fashion"
|
24 |
+
inputs = tokenizer(prompt, return_tensors="pt")
|
25 |
+
outputs = model.generate(**inputs, max_new_tokens=50)
|
26 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
27 |
+
|
28 |
+
|
29 |
+
---
|
30 |
+
license: mit
|
31 |
+
---
|