Instructions to use keras/blip2_opt_6.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/blip2_opt_6.7b with KerasHub:
import keras_hub # Load CausalLM model (optional: use half precision for inference) causal_lm = keras_hub.models.CausalLM.from_preset("hf://keras/blip2_opt_6.7b", dtype="bfloat16") causal_lm.compile(sampler="greedy") # (optional) specify a sampler # Generate text causal_lm.generate("Keras: deep learning for", max_length=64)import keras_hub # Create a Seq2SeqLM model task = keras_hub.models.Seq2SeqLM.from_preset("hf://keras/blip2_opt_6.7b")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/blip2_opt_6.7b") - Keras
How to use keras/blip2_opt_6.7b with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://keras/blip2_opt_6.7b") - Notebooks
- Google Colab
- Kaggle
| { | |
| "module": "keras_hub.src.models.blip2.blip2_image_converter", | |
| "class_name": "BLIP2ImageConverter", | |
| "config": { | |
| "name": "blip2_image_converter", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "image_size": [ | |
| 224, | |
| 224 | |
| ], | |
| "interpolation": "bicubic", | |
| "antialias": true, | |
| "crop_to_aspect_ratio": false, | |
| "pad_to_aspect_ratio": false, | |
| "bounding_box_format": "yxyx" | |
| }, | |
| "registered_name": "keras_hub>BLIP2ImageConverter" | |
| } |