allenai/dolma
Updated • 4.69k • 1.03k
How to use mlx-community/OLMo-1B-hf-4bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir OLMo-1B-hf-4bit-mlx mlx-community/OLMo-1B-hf-4bit-mlx
Configuration Parsing Warning:In UNKNOWN_FILENAME: "auto_map.AutoTokenizer" must be a string
This model was converted to MLX format from allenai/OLMo-1B.
Refer to the original model card for more details on the model.
pip install mlx-lm
pip install ai2-olmo
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/OLMo-1B-hf-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Quantized