Commit
•
c73687a
1
Parent(s):
feafc80
uploaded model
Browse files- config.json +91 -0
config.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bart-base-finetuned-xsum",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForCausalLM"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_decoder": true,
|
| 37 |
+
"is_encoder_decoder": false,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1,
|
| 41 |
+
"LABEL_2": 2
|
| 42 |
+
},
|
| 43 |
+
"max_position_embeddings": 1024,
|
| 44 |
+
"model_type": "bart",
|
| 45 |
+
"no_repeat_ngram_size": 3,
|
| 46 |
+
"normalize_before": false,
|
| 47 |
+
"normalize_embedding": true,
|
| 48 |
+
"num_beams": 4,
|
| 49 |
+
"num_hidden_layers": 6,
|
| 50 |
+
"pad_token_id": 1,
|
| 51 |
+
"quantization_config": {
|
| 52 |
+
"_load_in_4bit": false,
|
| 53 |
+
"_load_in_8bit": true,
|
| 54 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 55 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 56 |
+
"bnb_4bit_quant_type": "fp4",
|
| 57 |
+
"bnb_4bit_use_double_quant": false,
|
| 58 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 59 |
+
"llm_int8_has_fp16_weight": false,
|
| 60 |
+
"llm_int8_skip_modules": null,
|
| 61 |
+
"llm_int8_threshold": 6.0,
|
| 62 |
+
"load_in_4bit": false,
|
| 63 |
+
"load_in_8bit": true,
|
| 64 |
+
"quant_method": "bitsandbytes"
|
| 65 |
+
},
|
| 66 |
+
"scale_embedding": false,
|
| 67 |
+
"task_specific_params": {
|
| 68 |
+
"summarization": {
|
| 69 |
+
"length_penalty": 1.0,
|
| 70 |
+
"max_length": 128,
|
| 71 |
+
"min_length": 12,
|
| 72 |
+
"num_beams": 4
|
| 73 |
+
},
|
| 74 |
+
"summarization_cnn": {
|
| 75 |
+
"length_penalty": 2.0,
|
| 76 |
+
"max_length": 142,
|
| 77 |
+
"min_length": 56,
|
| 78 |
+
"num_beams": 4
|
| 79 |
+
},
|
| 80 |
+
"summarization_xsum": {
|
| 81 |
+
"length_penalty": 1.0,
|
| 82 |
+
"max_length": 62,
|
| 83 |
+
"min_length": 11,
|
| 84 |
+
"num_beams": 6
|
| 85 |
+
}
|
| 86 |
+
},
|
| 87 |
+
"torch_dtype": "float16",
|
| 88 |
+
"transformers_version": "4.40.2",
|
| 89 |
+
"use_cache": true,
|
| 90 |
+
"vocab_size": 50265
|
| 91 |
+
}
|