Instructions to use build-small-hackathon/tianwen-minicpm5-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use build-small-hackathon/tianwen-minicpm5-1b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="build-small-hackathon/tianwen-minicpm5-1b",
	filename="tianwen-minicpm1b.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use build-small-hackathon/tianwen-minicpm5-1b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf build-small-hackathon/tianwen-minicpm5-1b
# Run inference directly in the terminal:
llama-cli -hf build-small-hackathon/tianwen-minicpm5-1b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf build-small-hackathon/tianwen-minicpm5-1b
# Run inference directly in the terminal:
llama-cli -hf build-small-hackathon/tianwen-minicpm5-1b

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 build-small-hackathon/tianwen-minicpm5-1b
# Run inference directly in the terminal:
./llama-cli -hf build-small-hackathon/tianwen-minicpm5-1b

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 build-small-hackathon/tianwen-minicpm5-1b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf build-small-hackathon/tianwen-minicpm5-1b

Use Docker

docker model run hf.co/build-small-hackathon/tianwen-minicpm5-1b

LM Studio
Jan

vLLM

How to use build-small-hackathon/tianwen-minicpm5-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "build-small-hackathon/tianwen-minicpm5-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "build-small-hackathon/tianwen-minicpm5-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/build-small-hackathon/tianwen-minicpm5-1b

Ollama
How to use build-small-hackathon/tianwen-minicpm5-1b with Ollama:
```
ollama run hf.co/build-small-hackathon/tianwen-minicpm5-1b
```

Unsloth Studio

How to use build-small-hackathon/tianwen-minicpm5-1b 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 build-small-hackathon/tianwen-minicpm5-1b 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 build-small-hackathon/tianwen-minicpm5-1b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for build-small-hackathon/tianwen-minicpm5-1b to start chatting

How to use build-small-hackathon/tianwen-minicpm5-1b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf build-small-hackathon/tianwen-minicpm5-1b

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "build-small-hackathon/tianwen-minicpm5-1b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use build-small-hackathon/tianwen-minicpm5-1b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf build-small-hackathon/tianwen-minicpm5-1b

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default build-small-hackathon/tianwen-minicpm5-1b

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use build-small-hackathon/tianwen-minicpm5-1b with Docker Model Runner:
```
docker model run hf.co/build-small-hackathon/tianwen-minicpm5-1b
```

Lemonade

How to use build-small-hackathon/tianwen-minicpm5-1b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull build-small-hackathon/tianwen-minicpm5-1b

Run and chat with the model

lemonade run user.tianwen-minicpm5-1b-{{QUANT_TAG}}

List all available models

lemonade list

Tianwen · MiniCPM5-1B (fine-tuned)

A 1B model fine-tuned to read Chinese BaZi (八字) / I-Ching (六爻) charts in a warm, plain, second-person, anti-doom voice — translating esoteric symbols into everyday psychological language and always ending with one concrete next step. It powers the Tianwen app for the Build Small Hackathon.

Base model: openbmb/MiniCPM5-1B
Method: LoRA (rank 16, alpha 32, dropout 0.05, target=all), bf16, template="empty", cutoff_len=4096
Data: 58 distilled samples (teacher: MiniMax-M2.7-highspeed) — see tianwen-distill
Training: Modal A100, 8 epochs, lr 2e-4 cosine — train_loss 1.939, loss 3.5 → 1.0 in 91s
Formats: F16 GGUF (tianwen-minicpm1b.gguf, 2.1 GB) and a quantized Q4_K_M (~700 MB)

Intended use

Self-reflection and entertainment, inside the Tianwen app, over deterministically-computed chart data (lunar-python). The model only narrates; it does not compute dates or guarantee outcomes.

Run with llama.cpp

llama-server -m tianwen-minicpm1b-q4_k_m.gguf --port 8888 -c 4096
# OpenAI-compatible: POST /v1/chat/completions

Limitations

Chinese-only voice. Distillation data is Chinese; outputs trend Chinese even when prompted in English.
Small data (58 samples) fixes the style, not factual breadth — correctness rides on the chart inputs.
Not a safety system. Crisis handling lives in the app's deterministic guardrail, not in this model.

Reproduce

Distillation + training scripts: finetune/ · full build log: docs/FINETUNE_REPORT.md.

License

Fine-tune weights released under Apache-2.0, inheriting the base model's terms. For reflection and entertainment only — not medical, psychological, or financial advice.

Downloads last month: 3

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for build-small-hackathon/tianwen-minicpm5-1b

Base model

openbmb/MiniCPM5-1B

Adapter

(34)

this model

build-small-hackathon
/

tianwen-minicpm5-1b