neuron-testing-cache
/
neuronxcc-2.15.128.0+56dc5a86
/0_REGISTRY
/0.0.25.dev0
/inference
/albert
/hf-internal-testing
/tiny-random-AlbertModel
/d97c7cbbffd9b73dc964.json
{"architectures": ["AlbertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout_prob": 0.1, "embedding_size": 128, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 36, "initializer_range": 0.02, "inner_group_num": 1, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "albert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 32}, "num_attention_heads": 6, "num_hidden_groups": 6, "num_hidden_layers": 6, "position_embedding_type": "absolute", "task": "question-answering", "type_vocab_size": 16, "vocab_size": 30000} |