You can deploy this model and start earning money today!

TRI-ML/
Foundry-VLM-1.3B-165M

Name: Foundry-VLM-1.3B-165M
Availability: InStock

Views

No views yet

Foundry-VLM-1.3B-165M

A 1.3B parameter vision-language model trained on 165M image-caption samples, part of the VLA Foundry collection.

Architecture: ViT encoder (12 layers, 768 hidden dim, patch size 14, pixel-shuffle 2x) + Transformer decoder (24 layers, 2048 hidden dim, 16 heads)
Parameters: 1.3B (non-embedding)
Processor: SmolVLM2
Training data: 165M image-caption pairs from DataComp-DR-1B
LR schedule: Warmup + constant (no decay)
LLM backbone: Initialized from Foundry-LLM-1.2B-800B

Earlier checkpoint of the Foundry VLM. Used as the vision-language backbone for the Foundry-VLA-1.7B action models.

COCO-val captioning:

BLEU-1	BLEU-2	BLEU-3	BLEU-4	ROUGE-L	CIDEr
57.25	37.12	23.23	14.44	37.13	50.17

bash

git clone https://github.com/TRI-ML/vla_foundry.git
cd vla_foundry
pip install -e .

python

from vla_foundry.models.base_model import BaseModel
model = BaseModel.from_pretrained("TRI-ML/Foundry-VLM-1.3B-165M")