Instructions to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="build-small-hackathon/mind-of-tashi-micro-grpo-gguf",
	filename="mind-of-tashi-micro-grpo-Q4_K_M.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/mind-of-tashi-micro-grpo-gguf 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/mind-of-tashi-micro-grpo-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf build-small-hackathon/mind-of-tashi-micro-grpo-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 build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf build-small-hackathon/mind-of-tashi-micro-grpo-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 build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M

Use Docker

docker model run hf.co/build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "build-small-hackathon/mind-of-tashi-micro-grpo-gguf"
# 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/mind-of-tashi-micro-grpo-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M

Ollama
How to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf with Ollama:
```
ollama run hf.co/build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M
```

Unsloth Studio

How to use build-small-hackathon/mind-of-tashi-micro-grpo-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 build-small-hackathon/mind-of-tashi-micro-grpo-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 build-small-hackathon/mind-of-tashi-micro-grpo-gguf 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/mind-of-tashi-micro-grpo-gguf to start chatting

How to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf 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/mind-of-tashi-micro-grpo-gguf:Q4_K_M

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/mind-of-tashi-micro-grpo-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf 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/mind-of-tashi-micro-grpo-gguf:Q4_K_M

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/mind-of-tashi-micro-grpo-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf with Docker Model Runner:
```
docker model run hf.co/build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M
```

Lemonade

How to use build-small-hackathon/mind-of-tashi-micro-grpo-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull build-small-hackathon/mind-of-tashi-micro-grpo-gguf:Q4_K_M

Run and chat with the model

lemonade run user.mind-of-tashi-micro-grpo-gguf-Q4_K_M

List all available models

lemonade list

The Mind of Tashi — micro student (GRPO, GGUF)

The GRPO-trained student exported to GGUF for llama.cpp. Drop-in replacement for the SFT GGUF in the playable Space after an A/B (winning the game is not enough — the mind-scroll prose must hold up). Transformers source: …/mind-of-tashi-micro-grpo.

Build status: this GGUF is built at push time from the GRPO checkpoint — it does not exist as a by-product of training. Use the exact same recipe as the SFT GGUF.

Files (after build)

File	Approx size	Use
`mind-of-tashi-micro-grpo-Q4_K_M.gguf`	~256 MB	deployed candidate
`mind-of-tashi-micro-grpo-f16.gguf`	~786 MB	zero-loss reference

Build recipe (no compiled binary needed)

Download the GRPO transformers checkpoint with chat_template.jinja (a missing template silently yields a garbage GGUF).
python convert_hf_to_gguf.py <ckpt> --outtype f16 → f16 GGUF.

Quantise via the llama-cpp-python C binding:

import ctypes, llama_cpp
p = llama_cpp.llama_model_quantize_default_params()
p.ftype = 15  # LLAMA_FTYPE_MOSTLY_Q4_K_M
llama_cpp.llama_model_quantize(b"in-f16.gguf", b"out-Q4_K_M.gguf", ctypes.byref(p))

Grade via the format gate through llama-cpp-python (the real deploy path); ship Q4 if it clears ≥15/20 and stays within ~5 ladder points of f16.

⚠️ `norm_topk_prob` — required for llama.cpp

Inherited norm_topk_prob=true from SFT; llama.cpp's qwen3moe graph hardcodes norm_w=true and a mismatched checkpoint produces garbage on every llama.cpp runtime. (See the SFT GGUF card.)

Usage

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="build-small-hackathon/mind-of-tashi-micro-grpo-gguf",
    filename="mind-of-tashi-micro-grpo-Q4_K_M.gguf",
    n_ctx=4096, n_gpu_layers=0, logits_all=True,
)