Hugging Face's logo

nvidia
/
llama-nemoretriever-colembed-1b-v1

Visual Document Retrieval
Transformers
Safetensors
ColPali
multilingual
llama_nemoretrievercolembed
feature-extraction
text
image
vidore
multimodal-embedding
multilingual-embedding
Text-to-Visual Document (T→VD) retrieval
custom_code
Model card Files
xet
Community
6

fix: update `llm_config` and `vision_config` Initialization in Config

#6
by whybe-choi - opened
base: refs/heads/main
←
from: refs/pr/6
Discussion Files changed
+10
-4
whybe-choi

This PR addresses AttributeErrors caused by missing llm_config and vision_config attributes in the llama_NemoRetrieverColEmbedConfig configuration class.

The model fails to load or serialize config with:

AttributeError: 'llama_NemoRetrieverColEmbedConfig' object has no attribute 'llm_config'
AttributeError: 'llama_NemoRetrieverColEmbedConfig' object has no attribute 'vision_config'
fix: update `llm_config` and `vision_config` Initialization in Config8809e733
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment