Liquid Models
Collection
small, fast, different, a bit dry • 6 items • Updated • 1
How to use nightmedia/LFM2-350M-Math-dwq6-mlx with MLX:
# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]
# Generate text with mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("nightmedia/LFM2-350M-Math-dwq6-mlx")
prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)How to use nightmedia/LFM2-350M-Math-dwq6-mlx with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "nightmedia/LFM2-350M-Math-dwq6-mlx" --prompt "Once upon a time"
This model LFM2-350M-Math-dwq6-mlx was converted to MLX format from LiquidAI/LFM2-350M-Math using mlx-lm version 0.28.1.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("LFM2-350M-Math-dwq6-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
Quantized