README.md

metadata

base_model: HuggingFaceTB/SmolLM-360M
datasets:
  - Magpie-Align/Magpie-Pro-300K-Filtered
  - bigcode/self-oss-instruct-sc2-exec-filter-50k
  - teknium/OpenHermes-2.5
  - HuggingFaceTB/everyday-conversations-llama3.1-2k
language:
  - en
library_name: transformers
license: apache-2.0
tags:
  - alignment-handbook
  - trl
  - sft
  - mlx

mlx-community/SmolLM-360M-Instruct-8bit

The Model mlx-community/SmolLM-360M-Instruct-8bit was converted to MLX format from HuggingFaceTB/SmolLM-360M-Instruct using mlx-lm version 0.17.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/SmolLM-360M-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)