Instructions to use mitkox/phi-2-super-OpenHermes-2.5-moe-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mitkox/phi-2-super-OpenHermes-2.5-moe-mlx with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mitkox/phi-2-super-OpenHermes-2.5-moe-mlx") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mitkox/phi-2-super-OpenHermes-2.5-moe-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "mitkox/phi-2-super-OpenHermes-2.5-moe-mlx"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "mitkox/phi-2-super-OpenHermes-2.5-moe-mlx" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mitkox/phi-2-super-OpenHermes-2.5-moe-mlx", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
mitkox/phi-2-super-OpenHermes-2.5-moe-mlx
This model is a MoE merger of abacaj/phi-2-super with g-ronimo/phi-2-OpenHermes-2.5
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mitkox/phi-2-super-OpenHermes-2.5-moe-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 159
Model size
3B params
Tensor type
BF16
·
Hardware compatibility
Log In to add your hardware
Quantized