README.md

metadata

language:
  - en
license: llama3
tags:
  - finance
  - mlx
datasets:
  - Open-Orca/OpenOrca
  - GAIR/lima
  - WizardLM/WizardLM_evol_instruct_V2_196k

mlx-community/instruction-pretrain-finance-Llama3-8B-4bit

The Model mlx-community/instruction-pretrain-finance-Llama3-8B-4bit was converted to MLX format from instruction-pretrain/finance-Llama3-8B 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-finance-Llama3-8B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)