Hugging Face's logo

Yusra
/
quantize_model

Text2Text Generation
Transformers
PyTorch
led
Inference Endpoints
8-bit precision
Model card Files Community
quantize_model
File size: 1,779 Bytes 
decd9fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
 
{
  "_name_or_path": "./outputs/",
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "architectures": [
    "LEDForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "attention_window": [
    1024,
    1024,
    1024,
    1024,
    1024,
    1024,
    1024,
    1024,
    1024,
    1024,
    1024,
    1024
  ],
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "early_stopping": true,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "gradient_checkpointing": 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
  },
  "length_penalty": 2.0,
  "max_decoder_position_embeddings": 1024,
  "max_encoder_position_embeddings": 16384,
  "max_length": 512,
  "min_length": 100,
  "model_type": "led",
  "no_repeat_ngram_size": 3,
  "num_beams": 4,
  "num_hidden_layers": 12,
  "output_past": false,
  "pad_token_id": 1,
  "prefix": " ",
  "quantization_config": {
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": true,
    "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
  },
  "torch_dtype": "float16",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "vocab_size": 50265
}