Implementation:Open compass VLMEvalKit VisualGLM

Field	Value
source	VLMEvalKit
domain	Vision, Model_Architecture

Overview

VLM adapter for the VisualGLM model enabling benchmark evaluation in VLMEvalKit.

Description

VisualGLM inherits from BaseModel and wraps the VisualGLM model for use within the VLMEvalKit evaluation framework. It initializes the model and tokenizer/processor from a HuggingFace model path (default: THUDM/visualglm-6b) and provides the generate_inner method for inference. Requires SwissArmyTransformer (sat) package for model operation.

Usage

Register in vlmeval/config.py via supported_VLM and invoke through the standard evaluation pipeline.

Code Reference

Source: vlmeval/vlm/visualglm.py, Lines: L1-38
Import: from vlmeval.vlm.visualglm import VisualGLM

Signature:

class VisualGLM(BaseModel):
    INSTALL_REQ = False
    INTERLEAVE = False
    def __init__(self, model_path='THUDM/visualglm-6b', **kwargs): ...
    def generate_inner(self, message, dataset=None): ...

I/O Contract

Direction	Description
Inputs	message — list of dicts with type (text/image) and value; dataset — optional dataset name for custom prompting
Outputs	generate_inner() returns str (model response text)

Usage Examples

from vlmeval.vlm.visualglm import VisualGLM
model = VisualGLM(model_path='path/to/model')
response = model.generate_inner(message)

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment