Instructions to use RemySkye/MiniCPM5-1B-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RemySkye/MiniCPM5-1B-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RemySkye/MiniCPM5-1B-i1-GGUF",
	filename="MiniCPM5-1B-F32.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 RemySkye/MiniCPM5-1B-i1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RemySkye/MiniCPM5-1B-i1-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 RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RemySkye/MiniCPM5-1B-i1-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 RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RemySkye/MiniCPM5-1B-i1-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 RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use RemySkye/MiniCPM5-1B-i1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RemySkye/MiniCPM5-1B-i1-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": "RemySkye/MiniCPM5-1B-i1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M

Ollama
How to use RemySkye/MiniCPM5-1B-i1-GGUF with Ollama:
```
ollama run hf.co/RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M
```

Unsloth Studio

How to use RemySkye/MiniCPM5-1B-i1-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 RemySkye/MiniCPM5-1B-i1-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 RemySkye/MiniCPM5-1B-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RemySkye/MiniCPM5-1B-i1-GGUF to start chatting

How to use RemySkye/MiniCPM5-1B-i1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf RemySkye/MiniCPM5-1B-i1-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": "RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RemySkye/MiniCPM5-1B-i1-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 RemySkye/MiniCPM5-1B-i1-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 RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use RemySkye/MiniCPM5-1B-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M
```

Lemonade

How to use RemySkye/MiniCPM5-1B-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RemySkye/MiniCPM5-1B-i1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM5-1B-i1-GGUF-Q4_K_M

List all available models

lemonade list

RemySkye commited on 14 days ago

Commit

ec910dd

verified ·

1 Parent(s): 26da3bd

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ tags:
 # MiniCPM5-1B-i1-GGUF
-This repository contains GGUF format quantizations of the base model openbmb/MiniCPM5-1B. These models were generated using llama.cpp with an Importance Matrix (imatrix) - https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d
 ## Models Available
@@ -26,3 +26,6 @@ The collection includes a total of 26 files:
 * Baseline Formats: BF16, FP16, and FP32
 * Quantization Types: 23 different levels including IQ1_S, IQ2_XXS, Q4_K_M, and Q8_0
 * Importance Matrix: `imatrix.gguf` is included for reference or custom use

 # MiniCPM5-1B-i1-GGUF
+This repository contains GGUF format quantizations of the model openbmb/MiniCPM5-1B. These models were generated using llama.cpp with an Importance Matrix (imatrix) - https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d
 ## Models Available
 * Baseline Formats: BF16, FP16, and FP32
 * Quantization Types: 23 different levels including IQ1_S, IQ2_XXS, Q4_K_M, and Q8_0
 * Importance Matrix: `imatrix.gguf` is included for reference or custom use
+# NOTE
+Quantization below 4 bits may result in unacceptably low quality, particularly for a 1B parameter model, which is inherently more sensitive to such compression.