Instructions to use Jun1510/junai-models 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 Jun1510/junai-models 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 Jun1510/junai-models:Q4_K_M # Run inference directly in the terminal: llama cli -hf Jun1510/junai-models:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Jun1510/junai-models:Q4_K_M # Run inference directly in the terminal: llama cli -hf Jun1510/junai-models: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 Jun1510/junai-models:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Jun1510/junai-models:Q4_K_M
Use Docker
docker model run hf.co/Jun1510/junai-models:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use Jun1510/junai-models with Ollama:
ollama run hf.co/Jun1510/junai-models:Q4_K_M
- Unsloth Desktop
- Pi
How to use Jun1510/junai-models with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Jun1510/junai-models: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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Jun1510/junai-models:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Jun1510/junai-models with Docker Model Runner:
docker model run hf.co/Jun1510/junai-models:Q4_K_M
- Lemonade
How to use Jun1510/junai-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Jun1510/junai-models:Q4_K_M
Run and chat with the model
lemonade run user.junai-models-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Jun1510/junai-models with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Jun1510/junai-models: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://127.0.0.1:9931/v1 hermes config set model.default Jun1510/junai-models:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Jun1510/junai-models with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Jun1510/junai-models: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://127.0.0.1:9931/v1 \ --custom-model-id "Jun1510/junai-models: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"
Download knowledge/cooking.json from Jun1510/junai-models: direct link, hf CLI and curl.
- Browser
- Download file 5.55 kB
-
https://huggingface.co/Jun1510/junai-models/resolve/main/knowledge/cooking.json
- Command line
-
hf download hf://Jun1510/junai-models/knowledge/cooking.json
-
curl -L -o cooking.json https://huggingface.co/Jun1510/junai-models/resolve/main/knowledge/cooking.json
5.55 kB
| [ | |
| {"id": "cooking_001", "domain": "cooking", "topic": "how to boil the perfect egg", "content": "For a hard-boiled egg, place it in boiling water and cook for about 9-12 minutes, then transfer immediately to cold water to stop cooking. For a soft-boiled egg with a runny yolk, 5-6 minutes is typical."}, | |
| {"id": "cooking_002", "domain": "cooking", "topic": "difference between baking soda and baking powder", "content": "Baking soda is a pure alkaline compound that needs an acidic ingredient (like yogurt or lemon) to activate and help dough rise. Baking powder already contains an acid, so it can work on its own with just moisture and heat."}, | |
| {"id": "cooking_003", "domain": "cooking", "topic": "how to make basic rice", "content": "A common ratio for cooking white rice is 1 cup rice to about 1.5-2 cups water, brought to a boil then simmered covered for about 15-18 minutes, followed by a few minutes of resting off heat. Rinsing rice before cooking removes excess starch for fluffier results."}, | |
| {"id": "cooking_004", "domain": "cooking", "topic": "what is tempering (tadka) in Indian cooking", "content": "Tempering, or tadka, is a technique where whole spices (like cumin, mustard seeds, or dried chilies) are briefly fried in hot oil or ghee to release their flavor, then poured over a dish like dal or curry. It's typically the final step that adds aroma right before serving."}, | |
| {"id": "cooking_005", "domain": "cooking", "topic": "how to prevent rice from sticking or becoming mushy", "content": "Using the correct water ratio, not stirring rice too much while it cooks, and letting it rest covered for a few minutes after cooking helps keep grains separate rather than clumping. Rinsing rice before cooking also reduces excess surface starch that causes stickiness."}, | |
| {"id": "cooking_006", "domain": "cooking", "topic": "basic knife safety in the kitchen", "content": "Common kitchen knife safety practices include keeping knives sharp (a dull knife is more likely to slip), curling fingers away from the blade while cutting (\"claw grip\"), and never leaving a knife submerged in a sink of soapy water where it can't be seen."}, | |
| {"id": "cooking_007", "domain": "cooking", "topic": "how to store leftovers safely", "content": "Cooked food should generally be cooled and refrigerated within about 2 hours to prevent bacterial growth, stored in airtight containers, and consumed within about 3-4 days. Reheating leftovers thoroughly until steaming hot helps reduce food-safety risk."}, | |
| {"id": "cooking_008", "domain": "cooking", "topic": "what does marinating do", "content": "Marinating means soaking food, usually meat or vegetables, in a flavored liquid (often containing acid like lemon or yogurt, plus spices) before cooking. It adds flavor and can help tenderize the food, though very long acidic marinades can sometimes make meat texture mushy."}, | |
| {"id": "cooking_009", "domain": "cooking", "topic": "difference between simmering and boiling", "content": "Boiling means water is at a rolling, vigorous bubble at 100°C (212°F), while simmering is a gentler, lower-temperature cook with small bubbles just breaking the surface. Simmering is often used for soups, curries, and sauces to cook food gently without breaking it apart."}, | |
| {"id": "cooking_010", "domain": "cooking", "topic": "how to season food properly", "content": "A common tip is to season food gradually throughout cooking rather than all at the end, and taste as you go to adjust. Salt enhances existing flavors, while acid (like lemon or vinegar) can brighten a dish that tastes flat."}, | |
| {"id": "cooking_011", "domain": "cooking", "topic": "what is the Maillard reaction", "content": "The Maillard reaction is a chemical reaction between amino acids and sugars that occurs when food is cooked at high heat, producing browning and the deep, savory flavor seen in seared meat, toasted bread, or roasted vegetables. It requires relatively high, dry heat rather than boiling or steaming."}, | |
| {"id": "cooking_012", "domain": "cooking", "topic": "how to make a basic dal", "content": "A simple dal typically involves boiling lentils (like toor or moong dal) with turmeric and salt until soft, then finishing with a tempering (tadka) of cumin, garlic, and chili fried in ghee or oil poured over the top. Cooking time varies by lentil type, roughly 15-25 minutes in a pot or faster in a pressure cooker."}, | |
| {"id": "cooking_013", "domain": "cooking", "topic": "how to keep vegetables from overcooking", "content": "Vegetables retain more color, nutrients, and crunch when cooked briefly at higher heat (like stir-frying or blanching) rather than prolonged boiling. Plunging blanched vegetables into ice water afterward (\"shocking\") stops the cooking process immediately."}, | |
| {"id": "cooking_014", "domain": "cooking", "topic": "what is proofing dough", "content": "Proofing is the resting period where yeasted dough is left to rise, as the yeast produces carbon dioxide gas that makes the dough expand. A warm environment generally speeds up proofing, while refrigeration slows it for a more developed flavor over a longer time."}, | |
| {"id": "cooking_015", "domain": "cooking", "topic": "common substitutes when a recipe ingredient is missing", "content": "Common cooking substitutes include using yogurt or buttermilk in place of some cream, lemon juice plus milk as a buttermilk substitute, or applesauce in place of some oil in baking. Substitutions can slightly change texture or flavor, so they work best for non-critical ingredients."} | |
| ] | |