README.md

metadata

datasets:
  - instruction-pretrain/ft-instruction-synthesizer-collection
language:
  - en
license: apache-2.0
tags:
  - mlx

mlx-community/instruction-pretrain-instruction-synthesizer

The Model mlx-community/instruction-pretrain-instruction-synthesizer was converted to MLX format from instruction-pretrain/instruction-synthesizer using mlx-lm version 0.14.3. Original paper: Instruction Pre-Training: Language Models are Supervised Multitask Learners

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/instruction-pretrain-instruction-synthesizer")
response = generate(model, tokenizer, prompt="hello", verbose=True)