Safetensors
double_cast
DoubleCast / config.json
marcotet's picture
Upload folder using huggingface_hub
7707abe verified
{
"architectures": [
"DoubleCastModel"
],
"chronos_config": {
"context_length": 512,
"eos_token_id": 1,
"model_type": "seq2seq",
"n_special_tokens": 2,
"n_tokens": 4096,
"num_samples": 20,
"pad_token_id": 0,
"prediction_length": 64,
"temperature": 1.0,
"tokenizer_class": "MeanScaleUniformBins",
"tokenizer_kwargs": {
"high_limit": 15.0,
"low_limit": -15.0
},
"top_k": 50,
"top_p": 1.0,
"use_eos_token": true
},
"chronos_path": "amazon/chronos-t5-large",
"classifier_dropout": 0.0,
"cross_attention_model_size": 5120,
"d_ff": 4096,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dense_act_fn": "relu",
"dropout_rate": 0.1,
"dual_block_placement": [
"all"
],
"eos_token_id": 1,
"feed_forward_proj": "relu",
"initializer_factor": 0.05,
"is_encoder_decoder": true,
"is_gated_act": false,
"layer_norm_epsilon": 1e-06,
"model_type": "double_cast",
"n_positions": 512,
"num_decoder_layers": 24,
"num_heads": 16,
"num_layers": 24,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"text_encoder_layer_index": -2,
"text_encoder_path": "Qwen/Qwen3-14B",
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"vocab_size": 4096
}