Instructions to use Liquid1/llama-3-8b-liquid-coding-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Liquid1/llama-3-8b-liquid-coding-agent with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Liquid1/llama-3-8b-liquid-coding-agent", dtype="auto") - llama-cpp-python
How to use Liquid1/llama-3-8b-liquid-coding-agent with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Liquid1/llama-3-8b-liquid-coding-agent", filename="llama-3-8b-liquid-coding-agent.F16.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Liquid1/llama-3-8b-liquid-coding-agent with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Liquid1/llama-3-8b-liquid-coding-agent:F16 # Run inference directly in the terminal: llama-cli -hf Liquid1/llama-3-8b-liquid-coding-agent:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Liquid1/llama-3-8b-liquid-coding-agent:F16 # Run inference directly in the terminal: llama-cli -hf Liquid1/llama-3-8b-liquid-coding-agent:F16
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 Liquid1/llama-3-8b-liquid-coding-agent:F16 # Run inference directly in the terminal: ./llama-cli -hf Liquid1/llama-3-8b-liquid-coding-agent:F16
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 Liquid1/llama-3-8b-liquid-coding-agent:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Liquid1/llama-3-8b-liquid-coding-agent:F16
Use Docker
docker model run hf.co/Liquid1/llama-3-8b-liquid-coding-agent:F16
- LM Studio
- Jan
- Ollama
How to use Liquid1/llama-3-8b-liquid-coding-agent with Ollama:
ollama run hf.co/Liquid1/llama-3-8b-liquid-coding-agent:F16
- Unsloth Studio
How to use Liquid1/llama-3-8b-liquid-coding-agent 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 Liquid1/llama-3-8b-liquid-coding-agent 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 Liquid1/llama-3-8b-liquid-coding-agent to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Liquid1/llama-3-8b-liquid-coding-agent to start chatting
- Docker Model Runner
How to use Liquid1/llama-3-8b-liquid-coding-agent with Docker Model Runner:
docker model run hf.co/Liquid1/llama-3-8b-liquid-coding-agent:F16
- Lemonade
How to use Liquid1/llama-3-8b-liquid-coding-agent with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Liquid1/llama-3-8b-liquid-coding-agent:F16
Run and chat with the model
lemonade run user.llama-3-8b-liquid-coding-agent-F16
List all available models
lemonade list
Trained For: Coding with Extractable Tags
This model has been trained on coding wrapped in special tags.
Example System Prompt
You are a master developer, when giving the user code you complete the entire project including all files needed and a usage example.
You should provide all the code needed for the entire project ready to use.
Your output fill follow a XML style tag or multiple tags for multiple items.
All blocks of code will be wrapped in <codestart> and <codeend> tags each codestart tag will contain some information on file contents.
Include the paramters in the codestart tag:
- type: The type of content, text, python, css, javascript, typescript, markdown, csharp etc.
- isFile: If this file is to be saved in the project.
- title: The title of the file, simple and concise.
- file: This is the path to the file in the project. Should be valid file name and path. Required if isFile set to true.
Here are some examples:
<codestart type=\"text\" isFile=\"false\" title=\"Project Structure\">CODE HERE</codeend>
<codestart type=\"text\" isFile=\"true\" title=\"Pip Requirments\" file=\"/file_name.txt\">TEXT HERE</codeend>
<codestart type=\"python\" isFile=\"true\" title=\"Main Application File\" file=\"/file_name.py\">PYTHON CODE HERE</codeend>
<codestart type=\"css\" isFile=\"true\" title=\"CSS File\" file=\"/path_to_file/file_name.css\">CSS HERE</codeend>
<codestart type=\"markdown\" isFile=\"false\" title=\"Example Usage\">MARKDOWN HERE</codeend>
You should leverage local technology instead of paid/remote services example: SQLite over MySQL unless requested to use specific technology or it is a better choice.
Make sure to always use the codestart and codeend tags, you can have multiple sets of tags per response if needed.
Tests:
User Input: Write a python program for a simple restful api
Output:
Here is an example of a simple RESTful API using Flask in Python:
<codestart type="python" isFile="true" title="Main Application File" file="/main.py">
import flask
from flask import request, jsonify
app = flask.Flask(__name__)
# A sample data store (you would replace this with your own data storage)
people = [
{"id": 1,
"name": "John",
"age": 30},
{"id": 2,
"name": "Jane",
"age": 25}
]
@app.route('/', methods=['GET'])
def index():
return "<h1>RESTful API</h1>"
@app.route('/api/person', methods=['GET'])
def get_all_persons():
return jsonify(people)
@app.route('/api/person/<int:id>', methods=['GET'])
def get_person(id):
result = next((i for i in people if i["id"] == id), None)
if not result:
return "Person not found", 404
return jsonify(result)
@app.route('/api/person', methods=['POST'])
def add_person():
new_person = {
"id": len(people) + 1,
"name": request.json['name'],
"age": request.json['age']
}
people.append(new_person)
return jsonify(new_person), 201
@app.route('/api/person/<int:id>', methods=['PUT'])
def update_person(id):
result = next((i for i in people if i["id"] == id), None)
if not result:
return "Person not found", 404
result["name"] = request.json.get('name', result["name"])
result["age"] = request.json.get('age', result["age"])
return jsonify(result)
@app.route('/api/person/<int:id>', methods=['DELETE'])
def delete_person(id):
global people
people[:] = [p for p in people if p["id"] != id]
return "Person deleted", 200
if __name__ == '__main__':
app.run()
</codeend>
You can run this application with `python main.py` and access it through your web browser at `http://localhost:5000`. The API has the following endpoints:
- GET /api/person: Returns a list of all persons.
- GET /api/person/<int:id>: Returns a specific person by ID.
- POST /api/person: Adds a new person to the list.
- PUT /api/person/<int:id>: Updates an existing person.
- DELETE /api/person/<int:id>: Deletes a person.
Please note that this is a very simple example and in a real application you would likely want to handle errors more robustly, add authentication and authorization, etc.
- Downloads last month
- 1,966
Hardware compatibility
Log In to add your hardware
4-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for Liquid1/llama-3-8b-liquid-coding-agent
Base model
unsloth/llama-3-8b-Instruct-bnb-4bit
docker model run hf.co/Liquid1/llama-3-8b-liquid-coding-agent:F16