AraT5_msa_base_8bit / config.json
eaalghamdi's picture
Upload T5ForConditionalGeneration
ecd9461
raw
history blame
1.19 kB
{
"_name_or_path": "UBC-NLP/AraT5-msa-base",
"architectures": [
"T5ForConditionalGeneration"
],
"classifier_dropout": 0.0,
"d_ff": 2048,
"d_kv": 64,
"d_model": 768,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"gradient_checkpointing": false,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 12,
"num_heads": 12,
"num_layers": 12,
"output_past": true,
"pad_token_id": 0,
"quantization_config": {
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"torch_dtype": "float16",
"transformers_version": "4.32.0.dev0",
"use_cache": true,
"vocab_size": 110080
}