Instructions to use LH-Tech-AI/Apex-1.6-Instruct-350M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LH-Tech-AI/Apex-1.6-Instruct-350M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LH-Tech-AI/Apex-1.6-Instruct-350M",
	filename="apex_1.6.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LH-Tech-AI/Apex-1.6-Instruct-350M with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LH-Tech-AI/Apex-1.6-Instruct-350M
# Run inference directly in the terminal:
llama-cli -hf LH-Tech-AI/Apex-1.6-Instruct-350M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LH-Tech-AI/Apex-1.6-Instruct-350M
# Run inference directly in the terminal:
llama-cli -hf LH-Tech-AI/Apex-1.6-Instruct-350M

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 LH-Tech-AI/Apex-1.6-Instruct-350M
# Run inference directly in the terminal:
./llama-cli -hf LH-Tech-AI/Apex-1.6-Instruct-350M

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 LH-Tech-AI/Apex-1.6-Instruct-350M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LH-Tech-AI/Apex-1.6-Instruct-350M

Use Docker

docker model run hf.co/LH-Tech-AI/Apex-1.6-Instruct-350M

LM Studio
Jan

vLLM

How to use LH-Tech-AI/Apex-1.6-Instruct-350M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LH-Tech-AI/Apex-1.6-Instruct-350M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LH-Tech-AI/Apex-1.6-Instruct-350M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LH-Tech-AI/Apex-1.6-Instruct-350M

Ollama
How to use LH-Tech-AI/Apex-1.6-Instruct-350M with Ollama:
```
ollama run hf.co/LH-Tech-AI/Apex-1.6-Instruct-350M
```

Unsloth Studio new

How to use LH-Tech-AI/Apex-1.6-Instruct-350M 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 LH-Tech-AI/Apex-1.6-Instruct-350M 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 LH-Tech-AI/Apex-1.6-Instruct-350M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LH-Tech-AI/Apex-1.6-Instruct-350M to start chatting

Docker Model Runner
How to use LH-Tech-AI/Apex-1.6-Instruct-350M with Docker Model Runner:
```
docker model run hf.co/LH-Tech-AI/Apex-1.6-Instruct-350M
```

Lemonade

How to use LH-Tech-AI/Apex-1.6-Instruct-350M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LH-Tech-AI/Apex-1.6-Instruct-350M

Run and chat with the model

lemonade run user.Apex-1.6-Instruct-350M-{{QUANT_TAG}}

List all available models

lemonade list

This is our flagship!

Improved facts, chat instructions and coding!

Hey there! Welcome to Apex 1.6 Instruct 350M! We finetuned our base model of Apex 1 350M again! We now used a 2:1 ratio between Alpaca-Cleaned and Fineweb-Edu-10BT for anti-forgetting.

How to use it

You can download the apex_1.6.gguf or use ollama run hf.co/LH-Tech-AI/Apex-1.6-Instruct-350M. And you can also use it in LM Studio for example, just by searching for "Apex 1.6".

Have fun! :D

Downloads last month: 51

GGUF

Model size

0.4B params

Architecture

gpt2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Datasets used to train LH-Tech-AI/Apex-1.6-Instruct-350M

Collection including LH-Tech-AI/Apex-1.6-Instruct-350M

Our flagship CHAT models

Collection

This is a collection of all our flagship chat models to make it more easy for you! • 3 items • Updated 3 days ago