AuraFlow / text_encoder /config.json
isidentical's picture
Add fp16 variants to speedup loading and relax memory constraints (#15)
f16d500 verified
raw
history blame contribute delete
949 Bytes
{
"_name_or_path": "/raid/.cache/huggingface/models--fal--AuraFlow/snapshots/edf69bec4c8c57f5278a655aaca3ceb60d82c0b4/text_encoder",
"architectures": [
"UMT5EncoderModel"
],
"classifier_dropout": 0.0,
"d_ff": 5120,
"d_kv": 64,
"d_model": 2048,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 2,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "umt5",
"num_decoder_layers": 24,
"num_heads": 32,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"scalable_attention": true,
"tie_word_embeddings": false,
"tokenizer_class": "LlamaTokenizerFast",
"torch_dtype": "float16",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 32128
}