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

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 Settings

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

Atomic Chat new
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

Liquid1 commited on Jun 27, 2024

Commit

11ece75

verified ·

1 Parent(s): c869e75

Update README.md

Browse files

Files changed (1) hide show

README.md +33 -9

README.md CHANGED Viewed

@@ -4,19 +4,43 @@ language:
 - en
 license: apache-2.0
 tags:
-- text-generation-inference
-- transformers
-- unsloth
 - llama
 - gguf
 ---
-# Uploaded  model
-- **Developed by:** Liquid1
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - en
 license: apache-2.0
 tags:
 - llama
 - gguf
 ---
+# Trained For: Agent Calling
+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**:
+**Output**: