AiAF/Midnight-Miqu-70B-v1.5-MLX-2Bit
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("AiAF/Midnight-Miqu-70B-v1.5-MLX-2Bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 80
Model size
69B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
2-bit
Model tree for AiAF/Midnight-Miqu-70B-v1.5-MLX-2Bit
Base model
sophosympatheia/Midnight-Miqu-70B-v1.5