common-pile/comma_v0.1_training_dataset
Viewer • Updated • 784M • 15.2k • 44
How to use yunfengwang/comma-v0.1-1t-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("yunfengwang/comma-v0.1-1t-mlx")
prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)How to use yunfengwang/comma-v0.1-1t-mlx with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "yunfengwang/comma-v0.1-1t-mlx" --prompt "Once upon a time"
original model: https://huggingface.co/common-pile/comma-v0.1-1t
How to use:
uv run --python 3.12 \
--with mlx-lm \
mlx_lm.generate \
--model yunfengwang/comma-v0.1-1t-mlx \
--prompt 'The captial city of china is'
Quantized
Base model
common-pile/comma-v0.1-1t