Instructions to use hkondle/CapstoneMainModel-10ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hkondle/CapstoneMainModel-10ep with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="hkondle/CapstoneMainModel-10ep")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("hkondle/CapstoneMainModel-10ep") model = AutoModelForMultimodalLM.from_pretrained("hkondle/CapstoneMainModel-10ep", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "BlipForConditionalGeneration" | |
| ], | |
| "dtype": "float32", | |
| "image_text_hidden_size": 256, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "label_smoothing": 0.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "blip", | |
| "projection_dim": 512, | |
| "text_config": { | |
| "add_cross_attention": false, | |
| "attention_probs_dropout_prob": 0.0, | |
| "bos_token_id": 30522, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "dtype": "float32", | |
| "encoder_hidden_size": 768, | |
| "eos_token_id": 2, | |
| "finetuning_task": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": true, | |
| "label_smoothing": 0.0, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "blip_text_model", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "prefix": null, | |
| "projection_dim": 768, | |
| "pruned_heads": {}, | |
| "sep_token_id": 102, | |
| "task_specific_params": null, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "torchscript": false, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 30524 | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.0.0", | |
| "vision_config": { | |
| "add_cross_attention": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "dropout": 0.0, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "finetuning_task": null, | |
| "hidden_act": "gelu", | |
| "hidden_size": 768, | |
| "image_size": 384, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "blip_vision_model", | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": null, | |
| "patch_size": 16, | |
| "prefix": null, | |
| "projection_dim": 512, | |
| "pruned_heads": {}, | |
| "sep_token_id": null, | |
| "task_specific_params": null, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "torchscript": false, | |
| "use_bfloat16": false | |
| } | |
| } | |