dacorvo's picture
dacorvo HF staff
Synchronizing local compiler cache.
8c690bf verified
{
"_name_or_path": "hf-internal-testing/tiny-random-camembert",
"architectures": [
"CamembertModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 32,
"initializer_range": 0.02,
"intermediate_size": 37,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "camembert",
"neuron": {
"auto_cast": null,
"auto_cast_type": null,
"compiler_type": "neuronx-cc",
"compiler_version": "2.14.182.0+a56cbff7",
"disable_fallback": false,
"disable_fast_relayout": false,
"dynamic_batch_size": true,
"inline_weights_to_neff": true,
"input_names": [
"input_ids",
"attention_mask"
],
"model_type": "camembert",
"optlevel": "2",
"output_attentions": false,
"output_hidden_states": false,
"output_names": [
"logits"
],
"static_batch_size": 1,
"static_sequence_length": 32
},
"num_attention_heads": 4,
"num_hidden_layers": 5,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"task": "token-classification",
"torchscript": true,
"transformers_version": "4.41.1",
"type_vocab_size": 16,
"use_cache": true,
"vocab_size": 1000
}