README.md

metadata

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - alignment-handbook
  - trl
  - sft
  - mlx
base_model: HuggingFaceTB/SmolLM-135M
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

madroid/SmolLM-135M-Instruct-4bit

The Model madroid/SmolLM-135M-Instruct-4bit was converted to MLX format from HuggingFaceTB/SmolLM-135M-Instruct using mlx-lm version 0.17.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("madroid/SmolLM-135M-Instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)