|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- ParlAI/blended_skill_talk |
|
|
- convai-challenge/conv_ai_2 |
|
|
- allenai/social_i_qa |
|
|
language: |
|
|
- en |
|
|
- ru |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
- perplexity |
|
|
- bleu |
|
|
- rouge |
|
|
base_model: |
|
|
- SkillForge45/CyberFuture-1 |
|
|
new_version: SkillForge45/CyberFuture-2 |
|
|
pipeline_tag: text-generation |
|
|
library_name: transformers |
|
|
tags: |
|
|
- legal |
|
|
--- |
|
|
# CyberFuture-2 - New version of CyberFuture |
|
|
Uptades: |
|
|
**-Voice & Text chat** |
|
|
**-App.py directly from the model.py file, not from the repository** |
|
|
# Installation |
|
|
1. Clone the model: |
|
|
```bash |
|
|
git clone https://huggingface.co/SkillForge45/CyberFuture-2 |
|
|
``` |
|
|
2. Install all requirements: |
|
|
```bash |
|
|
pip install fastapi torch transformers tqdm pyttsx3 datasets speech_recognition pydantic univorn typing |
|
|
``` |
|
|
# Usage |
|
|
1. Train the model: |
|
|
```bash |
|
|
python model.py |
|
|
``` |
|
|
2. Launch the server: |
|
|
```bash |
|
|
python app.py |
|
|
``` |
|
|
3. Parse chat from server: |
|
|
```bash |
|
|
curl -X POST "http://localhost:8000/chat/" |
|
|
``` |
|
|
4. Start chatting: |
|
|
```bash |
|
|
-H "Content-Type: multipart/form-data" \ |
|
|
-F "prompt=YOUR_QUESTION_HERE" \ |
|
|
-F "max_length=50" \ |
|
|
-F "use_voice=false" #for text chat |
|
|
### .void |
|
|
-H "Content-Type: multipart/form-data" \ |
|
|
-F "[email protected]" \ |
|
|
-F "max_length=50" \ |
|
|
-F "use_voice=true" #for voice chat |
|
|
``` |
|
|
# License |
|
|
This model is licensed, see the "LICENSE" for more information |
|
|
|
|
|
<small><small>©2025 EidolonAI, "CyberFuture-2"<small><small> |
