Zero-Shot Image Classification
Transformers
Safetensors
sentence-transformers
mllama
image-text-to-text
mmeb
text-generation-inference
Instructions to use intfloat/mmE5-mllama-11b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use intfloat/mmE5-mllama-11b-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="intfloat/mmE5-mllama-11b-instruct") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("intfloat/mmE5-mllama-11b-instruct") model = AutoModelForImageTextToText.from_pretrained("intfloat/mmE5-mllama-11b-instruct") - sentence-transformers
How to use intfloat/mmE5-mllama-11b-instruct with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("intfloat/mmE5-mllama-11b-instruct") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
use only `<|image|>`
Browse files- custom_st.py +1 -1
custom_st.py
CHANGED
|
@@ -67,7 +67,7 @@ class MultiModalTransformer(BaseTransformer):
|
|
| 67 |
if sub_item["type"] == "text":
|
| 68 |
text += sub_item["content"]
|
| 69 |
elif sub_item["type"] in ["image_bytes", "image_path"]:
|
| 70 |
-
text += "<|image|>
|
| 71 |
if sub_item["type"] == "image_bytes":
|
| 72 |
img = Image.open(BytesIO(sub_item["content"])).convert("RGB")
|
| 73 |
else:
|
|
|
|
| 67 |
if sub_item["type"] == "text":
|
| 68 |
text += sub_item["content"]
|
| 69 |
elif sub_item["type"] in ["image_bytes", "image_path"]:
|
| 70 |
+
text += "<|image|>"
|
| 71 |
if sub_item["type"] == "image_bytes":
|
| 72 |
img = Image.open(BytesIO(sub_item["content"])).convert("RGB")
|
| 73 |
else:
|