rsonavane commited on
Commit
4783d74
1 Parent(s): 1693653

Upload 2 files

Browse files
Files changed (2) hide show
  1. config.json +67 -0
  2. generation_config.json +7 -0
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-xl",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 5120,
7
+ "d_kv": 64,
8
+ "d_model": 2048,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 32,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "quantization_config": {
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_8bit": true
30
+ },
31
+ "relative_attention_max_distance": 128,
32
+ "relative_attention_num_buckets": 32,
33
+ "task_specific_params": {
34
+ "summarization": {
35
+ "early_stopping": true,
36
+ "length_penalty": 2.0,
37
+ "max_length": 200,
38
+ "min_length": 30,
39
+ "no_repeat_ngram_size": 3,
40
+ "num_beams": 4,
41
+ "prefix": "summarize: "
42
+ },
43
+ "translation_en_to_de": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to German: "
48
+ },
49
+ "translation_en_to_fr": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to French: "
54
+ },
55
+ "translation_en_to_ro": {
56
+ "early_stopping": true,
57
+ "max_length": 300,
58
+ "num_beams": 4,
59
+ "prefix": "translate English to Romanian: "
60
+ }
61
+ },
62
+ "tie_word_embeddings": false,
63
+ "torch_dtype": "float16",
64
+ "transformers_version": "4.28.1",
65
+ "use_cache": true,
66
+ "vocab_size": 32128
67
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }