blenderbot-1B-distill / config.json
patrickvonplaten's picture
Update config.json
a10c0a6
{
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": true,
"architectures": [
"BlenderbotForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 2560,
"decoder_attention_heads": 32,
"decoder_ffn_dim": 10240,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"do_blenderbot_90_layernorm": true,
"dropout": 0.1,
"encoder_attention_heads": 32,
"encoder_ffn_dim": 10240,
"encoder_layerdrop": 0.0,
"encoder_layers": 2,
"eos_token_id": 2,
"extra_layer_norm": false,
"extra_pos_embeddings": 0,
"force_bos_token_to_be_generated": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"layernorm_variant": "prelayernorm",
"length_penalty": 0.65,
"max_length": 60,
"max_position_embeddings": 128,
"min_length": 20,
"model_type": "blenderbot",
"no_repeat_ngram_size": 3,
"normalize_before": true,
"normalize_embedding": false,
"num_beams": 10,
"num_hidden_layers": 2,
"pad_token_id": 0,
"scale_embedding": true,
"static_position_embeddings": false,
"unk_token_id": 3,
"use_cache": true,
"vocab_size": 8008
}