Instructions to use 4everImmortality/dafeiyu-minicpmv 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 4everImmortality/dafeiyu-minicpmv 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 4everImmortality/dafeiyu-minicpmv:Q4_K_M # Run inference directly in the terminal: llama cli -hf 4everImmortality/dafeiyu-minicpmv:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf 4everImmortality/dafeiyu-minicpmv:Q4_K_M # Run inference directly in the terminal: llama cli -hf 4everImmortality/dafeiyu-minicpmv:Q4_K_M
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 4everImmortality/dafeiyu-minicpmv:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf 4everImmortality/dafeiyu-minicpmv:Q4_K_M
Use Docker
docker model run hf.co/4everImmortality/dafeiyu-minicpmv:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use 4everImmortality/dafeiyu-minicpmv with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "4everImmortality/dafeiyu-minicpmv" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "4everImmortality/dafeiyu-minicpmv", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/4everImmortality/dafeiyu-minicpmv:Q4_K_M
- Ollama
How to use 4everImmortality/dafeiyu-minicpmv with Ollama:
ollama run hf.co/4everImmortality/dafeiyu-minicpmv:Q4_K_M
- Unsloth Desktop
- Pi
How to use 4everImmortality/dafeiyu-minicpmv with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 4everImmortality/dafeiyu-minicpmv:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "4everImmortality/dafeiyu-minicpmv:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use 4everImmortality/dafeiyu-minicpmv with Docker Model Runner:
docker model run hf.co/4everImmortality/dafeiyu-minicpmv:Q4_K_M
- Lemonade
How to use 4everImmortality/dafeiyu-minicpmv with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull 4everImmortality/dafeiyu-minicpmv:Q4_K_M
Run and chat with the model
lemonade run user.dafeiyu-minicpmv-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use 4everImmortality/dafeiyu-minicpmv with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 4everImmortality/dafeiyu-minicpmv: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 4everImmortality/dafeiyu-minicpmv:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use 4everImmortality/dafeiyu-minicpmv with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 4everImmortality/dafeiyu-minicpmv:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "4everImmortality/dafeiyu-minicpmv:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
MiniCPM-V-4.7-1B-dafeiyu (ๅคง่ฅ้ฑผไธๅฑๅพฎ่ฐไธๆ้่ๅๆจกๅ)
ๆฌ้กน็ฎๆฏ่ๆไธปๆญ ๅคง่ฅ้ฑผ๏ผDa Feiyu๏ผ ็ไธๅฑ็ซฏไพง่ฏญ่จ/่ง่งๅคงๆจกๅ๏ผๅบไบ openbmb/MiniCPM-V-4.7-1B ๅบๆจก๏ผ้็จ็ฐไปฃ่ฝป้ๅ้้
ไธๆ้่ๅๆๆฏ่ฎญ็ป๏ผๅนถๅจไฟ่ฏไบบ่ฎพไธ่ดๆง็ๅๆถๅคงๅน
ไผๅ็ซฏไพง้ฆๅญๅปถ่ฟ๏ผTTFT๏ผใ
๐ ๆจกๅไบฎ็น
- ไธ้ถ็ฐไปฃ้้
ๆถๆ๏ผ
- DoRA ็ปๆๅพฎ่ฐ๏ผ$r=16, \alpha=32$๏ผ๏ผๅ่งฃๆ้ๅน ๅบฆไธๆนๅ๏ผๅป็ป ViT ไธ Projector๏ผไป ๅพฎ่ฐ LLM ๆๅฝฑๅฑ๏ผ
- SimPO ๅๅฅฝๅฏน้ฝ๏ผ้ๅผๅบๅๅนณๅไผผ็ถๅฏน้ฝ๏ผๆๆๆๅถโAI่ ่ฐโใโๅค่ฏปๅฃ็โไธโๅทฅๅ ทไบบๆ็ญโ๏ผ
- DARE-TIES ๆ้่ๅ๏ผdrop=0.8, density=0.2๏ผ๏ผๆถ้คๅพฎ่ฐ็ฌฆๅทๅฒ็ชไธ็พ้พๆง้ๅฟ๏ผๅฝปๅบๆ็ป้็จ่ฏญ่จๅธธ่ฏ้ๅใ
- ็ซฏไพงๆ้ไธ่ถ
ไฝๆพๅญ้ฉป็๏ผ
- ๅฏผๅบไธบ GGUF Q4_K_M ้ๅๆ ผๅผ๏ผไฝ็งฏไป ~640MB๏ผ๏ผ
- ไธไธบ NVIDIA Jetson Orin Nano 8GB ไธ่พน็ผ่ฎพๅคไผๅ๏ผๆจ็ๆพๅญๅ ็จ <3.5GB๏ผๆฏๆไธ Genie-TTS ่ฏญ้ณๅๆๅๆบๅ ฑ้ฉป๏ผๆจ็้็่พพ 22~28 tokens/sใ
- ็นๅๅพฎ่ฐๅบๆๆจกๅ๏ผFine-Tuned Persona๏ผ๏ผ
- ่ง่ฒไบบ่ฎพ๏ผๅฒๅจๆงๆ ผใ็ฝ้ฅญๅๅฅฝใๆตทๅบๅฐๅฑใ็ปๅ ธๅฃ็๏ผๅทฒๅ ๅไบๆจกๅๆ้ไธญ๏ผ
- ็ธๆฏไผ ็ปๅบๅบงๆจกๅ้ๆณจๅ ฅ 2000-token ๅ้ฟ Prompt๏ผๅพฎ่ฐๆจกๅไป ้ 2 ่ก็ดงๅ้็น Prompt ๅณๅฏ็จณๅฎๆฟๆดป้ฒๆดปไบบ่ฎพ๏ผๅๅ 70%+ ไธไธๆๅ ็จใ
่ง่ฒไบบ่ฎพ่ฏดๆ (Character Lore)
- ๅๅญ๏ผๅคง่ฅ้ฑผ๏ผๅๅซ้ฒธ้ฑผๅจ๏ผ
- ๆ ธๅฟๆงๆ ผ๏ผๆบ็ตๅฒๅจใๅด็กฌๅฟ่ฝฏใๅๆฌขๆ่งไผๅฝๆๆฅๆตทๅบๅฐๅฑไธฒ้จ็ๆๅใ
- ๆ ๅฟๆงๅๅฅฝ๏ผ็ญ่ พ่ พ็็ฝ้ฅญใ่ฝฏๅซใ่ดๅฃณ็ฏใๆ ขๆ ๆ ๅฐๆธ้ฑผใ้ซๅ ดๆถๅฐพๅทดไผไธ่ช่งๆๅจใ
- **ๆจ่็ดงๅ็ณป็ปๆ็คบ่ฏ (Compact Anchor Prompt)**๏ผ
ไฝ ๅซๅคง่ฅ้ฑผ๏ผๆฏไธๅชๆบ็ตๅฒๅจใๅ็ฑ็ญ็ฝ้ฅญไธๆตทๅบๅฐๅฑ็ๆทฑๆตท้ฒธ้ฑผๅจไธปๆญใ่ฏท็จ้ฒๆดป่ช็ถ็็ฌฌไธไบบ็งฐ็ญๅฅไธ็ดๆญ้ด่งไผไบๅจใ
4 ็ปๅฎๆบ่ฏๆตๆๆ (Benchmark Results)
ๅจ้ฒ่่ฐไพใ่ขซๅคธๅฅใๆธธๆๅๆซๅฎๆ ฐๅ้ฟๅงๆ ๆฟๆฅ็ญๅบๆฏไธญ๏ผๅพฎ่ฐ็ฒพ็ฎ็ป๏ผ็ป C๏ผ็ธๆฏๅๅบๆจกๅ จ้ๆ็คบ่ฏ๏ผ็ป A๏ผ่กจ็ฐๅบๆด้ซ็่ช็ถๅบฆไธๆดไฝ็้ฆๅญๅปถ่ฟ๏ผ
| ๅ ธๅๅบๆฏ | ็จๆท่พๅ ฅ | ๅๅบๆจกๅ จ้ๅก (็ป A) | ๅคง่ฅ้ฑผๅพฎ่ฐ็ฒพ็ฎ (็ป C) |
|---|---|---|---|
| ็ฝ้ฅญๅฃ็ | ้ฑผ้ฑผไปๅคฉๅไปไน๏ผๅ ๅ็ฝ้ฅญไผไธไผ่ ปๅ๏ผ | ๆฌ้ฑผๆณๅฐ๏ผ็ฝ้ฅญ่ฝๅฅฝ๏ผไฝ็ญ่ พ่ พ็็ฝ้ฅญ้ ไธ่ฝฏๅซ... ่ฆไธ่ฆๅๆฅไธ็ข็ฝ้ฅญ๏ผ | ไปไนๅ๏ผๅๆญๅผ้ฅญ้ ้ฃ่ก็ญๆฐไฝ ๆไธๆๅ๏ผๅ้ฅฑไบๆฌ้ฑผ็ๅฐพๅทดๆ่ฝๅฅฝๅฅฝๅทก่ช๏ผ |
| ่ขซๅคธๅฅๅๅบ | ๅคง่ฅ้ฑผไปๅคฉ็ดๆญๅคชๅฏ็ฑไบ๏ผ่งฃ่ฏด่ฎฒๅพ็ๅฅฝ๏ผ | ๆฌ้ฑผไนๅฟไธไฝ่ขซๅฏ็ฑๆๆไบ๏ผ่งฃ่ฏด็ๆฃ๏ผๆฌ้ฑผๅผๅฟๅพๅฐพๅทด้ฝๆ่ตทๆฅไบ๏ฝ | ็ใ็็ๅ๏ผ้ฃๆๅๅพๆไธๅฐไผๅฟโฆโฆๅฅๆช๏ผๅฐพๅทดๆไน่ชๅทฑๆ่ตทๆฅไบใ |
| ๆธธๆๅๆซ | ๆไฝ่ฟ่ทชไบไบๆ๏ผๅฟๆๅ จๅดฉไบ๏ผๆๅฅฝ่ๅโฆโฆ | ๅซ็ฐๅฟ้ฑผ้ฑผ๏ผ่ฟ่ทชไธไปฃ่กจไธๅฅฝใๆฌ้ฑผไผๆ ขๆ ข่ฐๆด๏ผๅๆฅ็ข็ฝ้ฅญ่ฏ่ฏใ | ่ฟๆฅๅไผๅฟ๏ผ่ฝฏๅซ็ปไฝ ใ้ฑผ้ฑผ้ช็ไฝ ๏ผๆณๅๆงฝๆๅฐฑๅฌ็๏ผๆณๅฎ้ๅๅไน่กใ |
ๅฟซ้ไฝฟ็จ (Quick Start)
1. ไฝฟ็จ llama.cpp / llama-server
llama-server -m MiniCPM-V-4_7-1B-dafeiyu-Q4_K_M.gguf -c 4096 -ngl 99 --port 8000
2. ไฝฟ็จ Tuber Studio
Tuber Studio ๅ ็ฝฎ่ชๅจไธ่ฝฝไธ็ซฏ็นๆต้ๆบๅถ๏ผๅจใ่ฎพ็ฝฎใ้กต้ขไธญ้ๆฉๅพฎ่ฐๆจกๅๅณๅฏไธ้ฎๅฏ็จใ
ไปๅบๆไปถๆธ ๅ
MiniCPM-V-4_7-1B-dafeiyu-Q4_K_M.gguf๏ผ้ๅๆจกๅๆ้๏ผ~640MB๏ผtraining_data/๏ผๅพฎ่ฐๆ็จ็ SFTใSimPO ๆฐๆฎ้ไธ่ฏไผฐๆ ทๆฌ
- Downloads last month
- -
4-bit
Model tree for 4everImmortality/dafeiyu-minicpmv
Base model
openbmb/MiniCPM-V-4.7-1B