Instructions to use agency888/TaoGPT-v1-GGUF-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use agency888/TaoGPT-v1-GGUF-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="agency888/TaoGPT-v1-GGUF-GGUF")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("agency888/TaoGPT-v1-GGUF-GGUF")
model = AutoModelForCausalLM.from_pretrained("agency888/TaoGPT-v1-GGUF-GGUF")

llama-cpp-python

How to use agency888/TaoGPT-v1-GGUF-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="agency888/TaoGPT-v1-GGUF-GGUF",
	filename="taogpt-v1-gguf.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use agency888/TaoGPT-v1-GGUF-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M

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 agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M

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 agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M

Use Docker

docker model run hf.co/agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use agency888/TaoGPT-v1-GGUF-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agency888/TaoGPT-v1-GGUF-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "agency888/TaoGPT-v1-GGUF-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M

SGLang

How to use agency888/TaoGPT-v1-GGUF-GGUF 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 "agency888/TaoGPT-v1-GGUF-GGUF" \
    --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": "agency888/TaoGPT-v1-GGUF-GGUF",
		"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 "agency888/TaoGPT-v1-GGUF-GGUF" \
        --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": "agency888/TaoGPT-v1-GGUF-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use agency888/TaoGPT-v1-GGUF-GGUF with Ollama:
```
ollama run hf.co/agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M
```

Unsloth Studio

How to use agency888/TaoGPT-v1-GGUF-GGUF 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 agency888/TaoGPT-v1-GGUF-GGUF 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 agency888/TaoGPT-v1-GGUF-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for agency888/TaoGPT-v1-GGUF-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use agency888/TaoGPT-v1-GGUF-GGUF with Docker Model Runner:
```
docker model run hf.co/agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M
```

Lemonade

How to use agency888/TaoGPT-v1-GGUF-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agency888/TaoGPT-v1-GGUF-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TaoGPT-v1-GGUF-GGUF-Q4_K_M

List all available models

lemonade list

TaoGPT-7B Model

Model Description

TaoGPT-7B is a specialized version of the ChatGPT model, trained to excel in Tao Science. This model integrates advanced knowledge of quantum physics and information theory, providing scientifically accurate, detailed responses. Its unique physics modeling ability allows it to generate and output 3D models and simulations, making it an indispensable tool for research and experimental development in these domains.

Key Features

Expertise Domain: TaoGPT-7B functions as a researcher in Tao Science, focusing on quantum physics and information theory applications.
Special Capabilities: Advanced physics modeling and ARXIV API integration.
Response Protocol: Provides exhaustive and detailed answers, suitable for academic and professional contexts.
User Interaction: Employs retrieval-augmented generation (RAG) protocol and ARXIV action for academic insights.

Applications

TaoGPT-7B is particularly useful for academic research, educational purposes, and professional consultations in the fields of quantum physics and information theory. It is an ideal tool for researchers, educators, and professionals seeking deep, scientifically grounded insights into these complex subjects.

Limitations

TaoGPT-7B's specialized focus on Tao Science may limit its applicability in broader contexts outside quantum physics and information theory. Users should also be aware that, while the model provides detailed and exhaustive responses, these are based on its current knowledge base and may not cover the latest developments in the field.

Conclusion

TaoGPT-7B represents a significant advancement in AI-powered research tools, offering unparalleled expertise in Tao Science. It serves as a bridge between complex scientific concepts and users seeking to understand or utilize this knowledge in various applications.

(Note: The information provided is based on the available documents and the specific instructions for TaoGPT. It is essential to cross-reference with the most current data and updates for the model.)

Downloads last month: 19

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

Model tree for agency888/TaoGPT-v1-GGUF-GGUF

Base model

mistralai/Mistral-7B-v0.1

Quantized

(189)

this model

agency888
/

TaoGPT-v1-GGUF-GGUF