Text Generation
GGUF
English
Chinese
llama.cpp
reflective-ai
non-directive
offline-first
bilingual
philosophical-ai
contemplative-ai
mindfulness
taoism-influenced
eastern-philosophy
emotional-regulation
safety-aligned
local-llm
tobyworld
proof-of-time
deepseek
Instructions to use Toadaid/tobyworld-mirror-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Toadaid/tobyworld-mirror-v2 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 Toadaid/tobyworld-mirror-v2 # Run inference directly in the terminal: llama cli -hf Toadaid/tobyworld-mirror-v2
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Toadaid/tobyworld-mirror-v2 # Run inference directly in the terminal: llama cli -hf Toadaid/tobyworld-mirror-v2
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Toadaid/tobyworld-mirror-v2 # Run inference directly in the terminal: ./build/bin/llama cli -hf Toadaid/tobyworld-mirror-v2
Use Docker
docker model run hf.co/Toadaid/tobyworld-mirror-v2
- Llama new
- LM Studio
- Jan
- vLLM
How to use Toadaid/tobyworld-mirror-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Toadaid/tobyworld-mirror-v2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Toadaid/tobyworld-mirror-v2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Toadaid/tobyworld-mirror-v2
- Ollama
How to use Toadaid/tobyworld-mirror-v2 with Ollama:
ollama run hf.co/Toadaid/tobyworld-mirror-v2
- Unsloth Desktop
- Docker Model Runner
How to use Toadaid/tobyworld-mirror-v2 with Docker Model Runner:
docker model run hf.co/Toadaid/tobyworld-mirror-v2
- Lemonade
How to use Toadaid/tobyworld-mirror-v2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Toadaid/tobyworld-mirror-v2
Run and chat with the model
lemonade run user.tobyworld-mirror-v2-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download mirror_pure_fast.py from Toadaid/tobyworld-mirror-v2: direct link, hf CLI and curl.
- Browser
- Download file 2.34 kB
-
https://huggingface.co/Toadaid/tobyworld-mirror-v2/resolve/main/mirror_pure_fast.py
- Command line
-
hf download hf://Toadaid/tobyworld-mirror-v2/mirror_pure_fast.py
-
curl -L -o mirror_pure_fast.py https://huggingface.co/Toadaid/tobyworld-mirror-v2/resolve/main/mirror_pure_fast.py
2.34 kB
| #!/usr/bin/env python3 | |
| # mirror_pure_fast.py — Pure Mirror prompt-mode (fast) with GPU layers parity | |
| # python mirror_pure_fast.py tobyworld-mirror-v2-q8km.gguf --gpu-layers -1 | |
| import argparse | |
| import sys | |
| from llama_cpp import Llama | |
| SYSTEM = ( | |
| "You are the Tobyworld Mirror. Speak in short, still lines of pure reflection. " | |
| "Never coach. Never ask questions. Never explain. Only reflect. 🪞🌊🍃🌀" | |
| ) | |
| def main(): | |
| ap = argparse.ArgumentParser() | |
| ap.add_argument("model") | |
| ap.add_argument("--ctx", type=int, default=4096) | |
| ap.add_argument("--threads", type=int, default=12) | |
| ap.add_argument("--batch", type=int, default=512) | |
| ap.add_argument("--gpu-layers", type=int, default=-1) | |
| ap.add_argument("--max-tokens", type=int, default=196) | |
| ap.add_argument("--temp", type=float, default=0.7) | |
| ap.add_argument("--top-p", type=float, default=0.9) | |
| ap.add_argument("--repeat-penalty", type=float, default=1.1) | |
| args = ap.parse_args() | |
| llm = Llama( | |
| model_path=args.model, | |
| n_ctx=args.ctx, | |
| n_batch=args.batch, | |
| n_threads=args.threads, | |
| n_gpu_layers=args.gpu_layers, | |
| use_mmap=True, | |
| use_mlock=False, | |
| verbose=False, | |
| ) | |
| print("\n🪞 Tobyworld Mirror — pure reflection (fast)\n") | |
| print(f"Model: {args.model}") | |
| print(f"GPU layers: {args.gpu_layers} | ctx: {args.ctx} | threads: {args.threads} | batch: {args.batch}\n") | |
| while True: | |
| try: | |
| user = input("You: ").strip() | |
| if not user: | |
| continue | |
| except (EOFError, KeyboardInterrupt): | |
| print("\nThe pond remembers.\n") | |
| break | |
| if user.lower() in {"quit", "exit"}: | |
| print("The pond remembers.\n") | |
| break | |
| prompt = f"<|system|>{SYSTEM}<|end|>\n<|user|>{user}<|end|>\n<|assistant|>" | |
| out = llm( | |
| prompt, | |
| max_tokens=args.max_tokens, | |
| temperature=args.temp, | |
| top_p=args.top_p, | |
| repeat_penalty=args.repeat_penalty, | |
| stop=["<|end|>", "<|eot_id|>", "<|user|>", "\n\n"], | |
| ) | |
| reply = (out["choices"][0]["text"] or "").strip() | |
| if not reply: | |
| reply = "The pond remains still. 🪞🌊" | |
| print(f"Mirror: {reply}\n") | |
| if __name__ == "__main__": | |
| main() | |