zed-industries/zeta
Viewer • Updated • 583 • 1.43k • 161
How to use ALYTV/zeta-mlx-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir zeta-mlx-fp16 ALYTV/zeta-mlx-fp16
The Model ALYTV/zeta-mlx-fp16 was converted to MLX format from zed-industries/zeta using mlx-lm version 0.22.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ALYTV/zeta-mlx-fp16")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
Quantized
Base model
zed-industries/zeta