Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated
|
5 |
+
- flan-t5
|
6 |
+
- mental-health
|
7 |
+
- text2text-generation
|
8 |
+
- fine-tuned
|
9 |
+
- chatbot
|
10 |
+
- huggingface
|
11 |
+
datasets:
|
12 |
+
- mentalchat-16k
|
13 |
+
language:
|
14 |
+
- en
|
15 |
+
model-index:
|
16 |
+
- name: flan-t5-large-mentalchat
|
17 |
+
results: []
|
18 |
+
---
|
19 |
+
|
20 |
+
# 🧠 Flan-T5-Large Mental Health Chatbot
|
21 |
+
|
22 |
+
This is a fine-tuned version of `google/flan-t5-large` specifically tailored to act as a **mental health support assistant** trained on the **MentalChat-16k** dataset.
|
23 |
+
It can provide empathetic and supportive responses to mental health-related prompts, especially around anxiety, stress, overthinking, and low mood.
|
24 |
+
|
25 |
+
---
|
26 |
+
|
27 |
+
## 📊 Model Info
|
28 |
+
|
29 |
+
- **Base Model**: [`google/flan-t5-large`](https://huggingface.co/google/flan-t5-large)
|
30 |
+
- **Fine-tuned on**: MentalChat-16k Dataset
|
31 |
+
- **Framework**: Transformers + PyTorch
|
32 |
+
- **Task**: `text2text-generation`
|
33 |
+
- **Tokenizer**: AutoTokenizer from base model
|
34 |
+
- **Safe Format**: Safetensors
|
35 |
+
|
36 |
+
---
|
37 |
+
|
38 |
+
## 💬 Example Use
|
39 |
+
|
40 |
+
```python
|
41 |
+
from transformers import pipeline
|
42 |
+
|
43 |
+
chatbot = pipeline("text2text-generation", model="sarthak0226/flan-t5-large-mentalchat")
|
44 |
+
|
45 |
+
prompt = "I'm having trouble sleeping lately. What can I do?"
|
46 |
+
response = chatbot(prompt, max_length=100, do_sample=True, top_k=50, top_p=0.95)
|
47 |
+
|
48 |
+
print(response[0]["generated_text"])
|