metadata
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- vision-language
- multimodal
- agent
- zen
- hanzo
- zenlm
license: apache-2.0
Zen VL 8B Agent
Zen LM by Hanzo AI — Vision-language agent for advanced multimodal reasoning and tool use.
Specs
| Property | Value |
|---|---|
| Parameters | 8B |
| Context Length | 32,768 tokens |
| Architecture | Zen MoDE (Mixture of Distilled Experts) |
| Task | Vision-Language / Agent |
API Access
from openai import OpenAI
client = OpenAI(
base_url='https://api.hanzo.ai/v1',
api_key='your-api-key',
)
response = client.chat.completions.create(
model='zen-vl-8b-agent',
messages=[{
'role': 'user',
'content': [
{'type': 'text', 'text': 'Analyze this chart and summarize the trends.'},
{'type': 'image_url', 'image_url': {'url': 'https://example.com/chart.png'}},
],
}],
)
print(response.choices[0].message.content)
License
Apache 2.0