README.md

metadata

language:
  - zh
  - en
license: other
tags:
  - glm
  - chatglm
  - thudm
  - mlx
license_name: glm-4
license_link: https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/LICENSE
inference: false

tinywell/THUDM-glm-4-9b-chat-4bit

The Model tinywell/THUDM-glm-4-9b-chat-4bit was converted to MLX format from THUDM/glm-4-9b-chat using mlx-lm version 0.14.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("tinywell/THUDM-glm-4-9b-chat-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)