vikhyatk
/

moondream2

Image-Text-to-Text

text-generation

Inference Endpoints

Model card Files Files and versions Community

vikhyatk commited on Mar 6

Commit

eead139

•

1 Parent(s): c064b4c

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -8,7 +8,8 @@ moondream2 is a small vision language model designed to run efficiently on edge
 | Release | VQAv2 | GQA | TextVQA | POPE | TallyQA |
 | --- | --- | --- | --- | --- | --- |
-| **2024-03-04** (latest) | 74.2 | 58.5 | 36.4 | (coming soon) | (coming soon) |
 **Usage**
@@ -21,7 +22,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from PIL import Image
 model_id = "vikhyatk/moondream2"
-revision = "2024-03-05"
 model = AutoModelForCausalLM.from_pretrained(
     model_id, trust_remote_code=True, revision=revision
 )

 | Release | VQAv2 | GQA | TextVQA | POPE | TallyQA |
 | --- | --- | --- | --- | --- | --- |
+| 2024-03-04 | 74.2 | 58.5 | 36.4 | - | - |
+| **2024-03-06** (latest) | 75.4 | 59.8 | 43.1 | (coming soon) | (coming soon) |
 **Usage**
 from PIL import Image
 model_id = "vikhyatk/moondream2"
+revision = "2024-03-06"
 model = AutoModelForCausalLM.from_pretrained(
     model_id, trust_remote_code=True, revision=revision
 )