Instructions to use JIN223/gpt2_imdb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use JIN223/gpt2_imdb with KerasHub:
import keras_hub # Load CausalLM model (optional: use half precision for inference) causal_lm = keras_hub.models.CausalLM.from_preset("hf://JIN223/gpt2_imdb", 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 Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://JIN223/gpt2_imdb") - Keras
How to use JIN223/gpt2_imdb with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://JIN223/gpt2_imdb") - Notebooks
- Google Colab
- Kaggle
Download task.json from JIN223/gpt2_imdb: direct link, hf CLI and curl.
- Browser
- Download file 2.59 kB
-
https://huggingface.co/JIN223/gpt2_imdb/resolve/main/task.json
- Command line
-
hf download hf://JIN223/gpt2_imdb/task.json
-
curl -L -o task.json https://huggingface.co/JIN223/gpt2_imdb/resolve/main/task.json
2.59 kB
| { | |
| "module": "keras_hub.src.models.gpt2.gpt2_causal_lm", | |
| "class_name": "GPT2CausalLM", | |
| "config": { | |
| "backbone": { | |
| "module": "keras_hub.src.models.gpt2.gpt2_backbone", | |
| "class_name": "GPT2Backbone", | |
| "config": { | |
| "name": "gpt2_backbone", | |
| "trainable": true, | |
| "vocabulary_size": 50257, | |
| "num_layers": 12, | |
| "num_heads": 12, | |
| "hidden_dim": 768, | |
| "intermediate_dim": 3072, | |
| "dropout": 0.1, | |
| "max_sequence_length": 1024 | |
| }, | |
| "registered_name": "keras_hub>GPT2Backbone" | |
| }, | |
| "preprocessor": { | |
| "module": "keras_hub.src.models.gpt2.gpt2_causal_lm_preprocessor", | |
| "class_name": "GPT2CausalLMPreprocessor", | |
| "config": { | |
| "name": "gpt2_causal_lm_preprocessor", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "tokenizer": { | |
| "module": "keras_hub.src.models.gpt2.gpt2_tokenizer", | |
| "class_name": "GPT2Tokenizer", | |
| "config": { | |
| "name": "gpt2_tokenizer", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "int32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "config_file": "tokenizer.json", | |
| "sequence_length": null, | |
| "add_prefix_space": false, | |
| "unsplittable_tokens": [ | |
| "<|endoftext|>" | |
| ] | |
| }, | |
| "registered_name": "keras_hub>GPT2Tokenizer" | |
| }, | |
| "config_file": "preprocessor.json", | |
| "sequence_length": 1024, | |
| "add_start_token": true, | |
| "add_end_token": true | |
| }, | |
| "registered_name": "keras_hub>GPT2CausalLMPreprocessor" | |
| }, | |
| "name": "gpt2_causal_lm" | |
| }, | |
| "registered_name": "keras_hub>GPT2CausalLM" | |
| } |