Instructions to use AlexHung29629/gemma-4-e4b-it-text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AlexHung29629/gemma-4-e4b-it-text with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="AlexHung29629/gemma-4-e4b-it-text")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("AlexHung29629/gemma-4-e4b-it-text") model = AutoModel.from_pretrained("AlexHung29629/gemma-4-e4b-it-text") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Gemma4TextModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_k_eq_v": false, | |
| "bos_token_id": 2, | |
| "dtype": "bfloat16", | |
| "enable_moe_block": false, | |
| "eos_token_id": 1, | |
| "expert_intermediate_size": null, | |
| "final_logit_softcapping": 30.0, | |
| "global_head_dim": 512, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2560, | |
| "hidden_size_per_layer_input": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma4_text", | |
| "moe_intermediate_size": null, | |
| "num_attention_heads": 8, | |
| "num_experts": null, | |
| "num_global_key_value_heads": null, | |
| "num_hidden_layers": 42, | |
| "num_key_value_heads": 2, | |
| "num_kv_shared_layers": 18, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 1000000.0, | |
| "rope_type": "proportional" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 512, | |
| "tie_word_embeddings": true, | |
| "top_k_experts": null, | |
| "transformers_version": "5.5.0", | |
| "use_bidirectional_attention": null, | |
| "use_cache": true, | |
| "use_double_wide_mlp": false, | |
| "vocab_size": 262144, | |
| "vocab_size_per_layer_input": 262144 | |
| } | |