metadata
frameworks:
- Pytorch
license: other
license_name: glm-4
license_link: LICENSE
pipeline_tag: text-generation
tags:
- glm
- edge
- mlx
inference: false
base_model: zai-org/glm-edge-4b-chat
library_name: mlx
FalconDev25/glm-edge-4b-chat-4bit
This model FalconDev25/glm-edge-4b-chat-4bit was converted to MLX format from zai-org/glm-edge-4b-chat using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("FalconDev25/glm-edge-4b-chat-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)