Instructions to use internlm/internlm-xcomposer2d5-7b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use internlm/internlm-xcomposer2d5-7b-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="internlm/internlm-xcomposer2d5-7b-4bit")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("internlm/internlm-xcomposer2d5-7b-4bit", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Triton error when running the transformers version
#6
by frutiemax - opened
I have this error when trying to run the example transformers code:
# Unpack and reorder: shift out the correct 4-bit value and mask.
iweights = (iweights >> shifts) & 0xF
^
IncompatibleTypeErrorImpl('invalid operands of type triton.language.float16 and triton.language.float16')
I have transformers==4.53.0, triton=3.3.1 and torch=2.7.1.
Also, when I try to run the lmdeploy version, I am getting this error:
AttributeError: module 'transformers_modules.28ddb4078592cab81ed39af8900348c61223b2b3.modeling_internlm_xcomposer2' has no attribute 'get_font'