Instructions to use vcadillo/glm-4v-9b-4-bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vcadillo/glm-4v-9b-4-bits with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="vcadillo/glm-4v-9b-4-bits", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vcadillo/glm-4v-9b-4-bits", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
not work
#1
by willkang - opened
ValueError: Unrecognized configuration class <class 'transformers_modules.glm-4v-9b-4-bits.configuration_chatglm.ChatGLMConfig'> to build an AutoTokenizer.
Name: torch
Version: 2.2.2+cu121
Name: transformers
Version: 4.37.0
Name: torchvision
Version: 0.17.2+cu121
Thanks for your report, now was updated with the source glm-4v tokenizer as it was missing.
vcadillo changed discussion status to closed