Instructions to use SkillForge45/CyberFuture-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SkillForge45/CyberFuture-3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SkillForge45/CyberFuture-3")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SkillForge45/CyberFuture-3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SkillForge45/CyberFuture-3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SkillForge45/CyberFuture-3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SkillForge45/CyberFuture-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SkillForge45/CyberFuture-3
- SGLang
How to use SkillForge45/CyberFuture-3 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "SkillForge45/CyberFuture-3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SkillForge45/CyberFuture-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "SkillForge45/CyberFuture-3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SkillForge45/CyberFuture-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SkillForge45/CyberFuture-3 with Docker Model Runner:
docker model run hf.co/SkillForge45/CyberFuture-3
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,81 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- ParlAI/blended_skill_talk
|
| 5 |
+
- convai-challenge/conv_ai_2
|
| 6 |
+
- allenai/social_i_qa
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
- ru
|
| 10 |
+
metrics:
|
| 11 |
+
- accuracy
|
| 12 |
+
- precision
|
| 13 |
+
- recall
|
| 14 |
+
- perplexity
|
| 15 |
+
- bleu
|
| 16 |
+
- rouge
|
| 17 |
+
base_model:
|
| 18 |
+
- SkillForge45/CyberFuture-1
|
| 19 |
+
new_version: SkillForge45/CyberFuture-2
|
| 20 |
+
pipeline_tag: text-generation
|
| 21 |
+
library_name: transformers
|
| 22 |
+
tags:
|
| 23 |
+
- legal
|
| 24 |
+
---
|
| 25 |
+
# CyberFuture - Chat With AI
|
| 26 |
+
Uptades:
|
| 27 |
+
**-Web Search**
|
| 28 |
+
# Installation
|
| 29 |
+
1. Clone the model:
|
| 30 |
+
```bash
|
| 31 |
+
git clone https://huggingface.co/SkillForge45/CyberFuture-3
|
| 32 |
+
```
|
| 33 |
+
2. Install all requirements:
|
| 34 |
+
```bash
|
| 35 |
+
pip install torch transformers datasets googlesearch-python pyttsx3 speechrecognition fastapi uvicorn
|
| 36 |
+
```
|
| 37 |
+
# Usage
|
| 38 |
+
**METHOD #1 (HTML web interface):**
|
| 39 |
+
1. Launch the server:
|
| 40 |
+
```bash
|
| 41 |
+
python app.py
|
| 42 |
+
```
|
| 43 |
+
2. Start the HTML file (html_main.html)
|
| 44 |
+
**METHOD #2 (Python Uasge)**
|
| 45 |
+
Use this Python code:
|
| 46 |
+
```python
|
| 47 |
+
from model import ChatBot
|
| 48 |
+
|
| 49 |
+
# Initialize the chatbot
|
| 50 |
+
bot = ChatBot()
|
| 51 |
+
|
| 52 |
+
# Optionally train the model (requires GPU for good performance)
|
| 53 |
+
bot.train(epochs=3)
|
| 54 |
+
|
| 55 |
+
# Chat with web search
|
| 56 |
+
response = bot.generate_response("What's the latest news about AI?", use_web=True)
|
| 57 |
+
print(response)
|
| 58 |
+
|
| 59 |
+
# Voice interaction (requires microphone)
|
| 60 |
+
bot.voice_interface.speak(response)
|
| 61 |
+
user_input = bot.voice_interface.listen()
|
| 62 |
+
```
|
| 63 |
+
**METHOD #3 (Console)**
|
| 64 |
+
1. Text Chat:
|
| 65 |
+
```bash
|
| 66 |
+
curl -X POST "http://localhost:8000/chat/" \
|
| 67 |
+
-H "Content-Type: application/x-www-form-urlencoded" \
|
| 68 |
+
-d "prompt=What's the weather in London today?&use_web=true" #web search, if you not need web: use_web=False
|
| 69 |
+
```
|
| 70 |
+
2. Voice Chat:
|
| 71 |
+
```bash
|
| 72 |
+
curl -X POST "http://localhost:8000/chat/" \
|
| 73 |
+
-F "audio_file=@your_recording.wav" \
|
| 74 |
+
-F "use_web=true" \
|
| 75 |
+
-F "use_voice=true"
|
| 76 |
+
```
|
| 77 |
+
**METHOD 4 (Server)**
|
| 78 |
+
Start the app.py and go to http://localhost:8000/chat
|
| 79 |
+
# License
|
| 80 |
+
This model is licensed, see the LICENSE for more information
|
| 81 |
+
|