Update README.md
Browse files
README.md
CHANGED
@@ -21,14 +21,41 @@ widget:
|
|
21 |
content: >-
|
22 |
My best friend recently lost their parent to cancer after a long battle.
|
23 |
They are understandably devastated and struggling with grief.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
inference:
|
25 |
parameters:
|
26 |
max_new_tokens: 1024
|
27 |
-
do_sample: true
|
28 |
license: mit
|
29 |
---
|
30 |
|
31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
```python
|
33 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
34 |
device = "cuda" # the device to load the model onto
|
|
|
21 |
content: >-
|
22 |
My best friend recently lost their parent to cancer after a long battle.
|
23 |
They are understandably devastated and struggling with grief.
|
24 |
+
- example_title: EMO 3x
|
25 |
+
messages:
|
26 |
+
- role: system
|
27 |
+
content: >-
|
28 |
+
You are a helpful and emotional assistant that will always respond in EMO
|
29 |
+
style.
|
30 |
+
- role: user
|
31 |
+
content: >-
|
32 |
+
I'm feeling really down today. Can you cheer me up?
|
33 |
inference:
|
34 |
parameters:
|
35 |
max_new_tokens: 1024
|
|
|
36 |
license: mit
|
37 |
---
|
38 |
|
39 |
+
|
40 |
+
# EMO-1.5B: Emotionally Minded Oracle
|
41 |
+
|
42 |
+
EMO-1.5B is a powerful language model designed to engage in emotionally intelligent conversations. The full form of EMO stands for "Emotionally Minded Oracle," reflecting the model's ability to understand and express a wide range of human emotions.
|
43 |
+
|
44 |
+
## Overview
|
45 |
+
|
46 |
+
EMO-1.5B is a state-of-the-art conversational AI model with 1.5 billion parameters. It has been fine-tuned on a diverse corpus of emotional narratives, enabling it to perceive and respond to the emotional undertones present in user inputs. Whether you're seeking comfort, motivation, or simply an empathetic listener, EMO-1.5B is here to provide emotional support and guidance.
|
47 |
+
|
48 |
+
## Key Features
|
49 |
+
|
50 |
+
- **Emotional Intelligence**: EMO-1.5B can recognize and respond to various emotions, such as sadness, joy, anger, and fear, with appropriate emotional responses.
|
51 |
+
- **Contextual Understanding**: The model considers the broader context of the conversation to provide relevant and emotionally resonant responses.
|
52 |
+
- **Empathetic Dialogue**: EMO-1.5B excels at active listening, validating emotions, and offering compassionate advice or consolation when needed.
|
53 |
+
- **Adaptive Persona**: The model can adapt its persona and communication style to match the user's emotional state, providing a personalized and tailored experience.
|
54 |
+
|
55 |
+
## Usage
|
56 |
+
|
57 |
+
You can easily interact with EMO-1.5B using the provided example code:
|
58 |
+
|
59 |
```python
|
60 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
61 |
device = "cuda" # the device to load the model onto
|