Instructions to use rexprimematrix/RiShreAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use rexprimematrix/RiShreAI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="rexprimematrix/RiShreAI", filename="Phi-3-mini-4k-instruct-q4.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use rexprimematrix/RiShreAI with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf rexprimematrix/RiShreAI # Run inference directly in the terminal: llama-cli -hf rexprimematrix/RiShreAI
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf rexprimematrix/RiShreAI # Run inference directly in the terminal: llama-cli -hf rexprimematrix/RiShreAI
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf rexprimematrix/RiShreAI # Run inference directly in the terminal: ./llama-cli -hf rexprimematrix/RiShreAI
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf rexprimematrix/RiShreAI # Run inference directly in the terminal: ./build/bin/llama-cli -hf rexprimematrix/RiShreAI
Use Docker
docker model run hf.co/rexprimematrix/RiShreAI
- LM Studio
- Jan
- Ollama
How to use rexprimematrix/RiShreAI with Ollama:
ollama run hf.co/rexprimematrix/RiShreAI
- Unsloth Studio new
How to use rexprimematrix/RiShreAI with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for rexprimematrix/RiShreAI to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for rexprimematrix/RiShreAI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for rexprimematrix/RiShreAI to start chatting
- Docker Model Runner
How to use rexprimematrix/RiShreAI with Docker Model Runner:
docker model run hf.co/rexprimematrix/RiShreAI
- Lemonade
How to use rexprimematrix/RiShreAI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull rexprimematrix/RiShreAI
Run and chat with the model
lemonade run user.RiShreAI-{{QUANT_TAG}}List all available models
lemonade list
Create brain.py
Browse files
brain.py
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from flask import Flask, request, jsonify
|
| 2 |
+
from flask_cors import CORS
|
| 3 |
+
from gpt4all import GPT4All
|
| 4 |
+
import os
|
| 5 |
+
|
| 6 |
+
app = Flask(__name__)
|
| 7 |
+
# Sabhi connections allow karne ke liye CORS setup
|
| 8 |
+
CORS(app)
|
| 9 |
+
|
| 10 |
+
# --- CONFIGURATION ---
|
| 11 |
+
# Note: Is code mein hum model ko seedha tumhari naye repository se load karenge
|
| 12 |
+
MODEL_NAME = "Phi-3-mini-4k-instruct-q4.gguf"
|
| 13 |
+
REPO_ID = "rexprimematrix/RiShreAI" # Tumhara model repository
|
| 14 |
+
|
| 15 |
+
print(f"🔄 RiShre AI is waking up... Loading {MODEL_NAME}")
|
| 16 |
+
|
| 17 |
+
try:
|
| 18 |
+
# Ye gpt4all ko batayega ki file Hugging Face repo se download/load karni hai
|
| 19 |
+
model = GPT4All(MODEL_NAME, model_path=".", allow_download=True)
|
| 20 |
+
print("✅ RiShre AI Core is now ONLINE and Ready!")
|
| 21 |
+
except Exception as e:
|
| 22 |
+
print(f"❌ Critical Error: {e}")
|
| 23 |
+
|
| 24 |
+
@app.route('/', methods=['GET'])
|
| 25 |
+
def health_check():
|
| 26 |
+
return "RiShre AI Server is Running!"
|
| 27 |
+
|
| 28 |
+
@app.route('/api/chat', methods=['POST'])
|
| 29 |
+
def chat():
|
| 30 |
+
try:
|
| 31 |
+
data = request.json
|
| 32 |
+
user_msg = data.get("message", "")
|
| 33 |
+
|
| 34 |
+
if not user_msg:
|
| 35 |
+
return jsonify({"error": "No message provided"}), 400
|
| 36 |
+
|
| 37 |
+
# AI Response Generation
|
| 38 |
+
with model.chat_session():
|
| 39 |
+
response = model.generate(prompt=user_msg, max_tokens=300)
|
| 40 |
+
|
| 41 |
+
return jsonify({"text": response})
|
| 42 |
+
|
| 43 |
+
except Exception as e:
|
| 44 |
+
return jsonify({"error": str(e)}), 500
|
| 45 |
+
|
| 46 |
+
if __name__ == "__main__":
|
| 47 |
+
# Hugging Face Spaces strictly port 7860 hi use karta hai
|
| 48 |
+
app.run(host="0.0.0.0", port=7860)
|