metadata
license: other
license_name: deepseek
license_link: https://github.com/deepseek-ai/DeepSeek-MoE/blob/main/LICENSE-MODEL
tags:
- mlx
base_model: deepseek-ai/deepseek-moe-16b-chat
BlueMoonlight/deepseek-moe-16b-chat-mlx-4Bit
The Model BlueMoonlight/deepseek-moe-16b-chat-mlx-4Bit was converted to MLX format from deepseek-ai/deepseek-moe-16b-chat using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("BlueMoonlight/deepseek-moe-16b-chat-mlx-4Bit")
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)