Model reference · open weights
gregg-vision.1 is an open-weight language model from grascii. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | grascii |
|---|---|
| Type | Language models |
| Task | Image→text |
| Parameters (lead) | 36M |
| Runs with | transformers |
| Released | 2024-12-06 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
Gregg Vision v0.2.1 generates a Grascii representation of a Gregg Shorthand form.
Given a grayscale image of a single shorthand form, Gregg Vision can be used to generate its Grascii representation. When combined with Grascii Search, one can obtain possible English interpretations of the shorthand form.
Use the code below to get started with the model.
from transformers import AutoModelForVision2Seq, AutoImageProcessor, AutoTokenizer
from PIL import Image
import numpy as np
model_id = "grascii/gregg-vision-v0.2.1"
model = AutoModelForVision2Seq.from_pretrained(model_id)
processor = AutoImageProcessor.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
def generate_grascii(image: Image):
# convert image to a single channel
grayscale = image.convert("L")
# prepare processor input
images = np.array([grayscale])
# preprocess image
pixel_values = processor(images, return_tensors="pt").pixel_values
# generate token ids
ids = model.generate(pixel_values, max_new_tokens=12)[0]
# decode ids and return grascii
return tokenizer.decode(ids, skip_special_tokens=True)
Note: As of transformers v4.47.0, the model is incompatible with pipeline due to the
model's single channel image input.
Gregg Vision v0.2.1 is a transformer model with a ViT encoder and a Roberta decoder.
For training, the model was warm-started using vit-small-patch16-224-single-channel for the encoder and a randomly initialized Roberta network for the decoder.
Gregg Vision v0.2.1 was trained on the gregg-preanniversary-words dataset.
Gregg Vision v0.2.1 was trained using 1xT4.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys gregg-vision-1 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (gregg-vision-1 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gregg-vision-1","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.