marcchew commited on
Commit
59e1509
1 Parent(s): 30d8774

Upload T5ForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +73 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MBZUAI/LaMini-T5-223M",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "quantization_config": {
27
+ "bnb_4bit_compute_dtype": "float32",
28
+ "bnb_4bit_quant_type": "fp4",
29
+ "bnb_4bit_use_double_quant": false,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": false,
35
+ "load_in_8bit": true,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "relative_attention_max_distance": 128,
39
+ "relative_attention_num_buckets": 32,
40
+ "task_specific_params": {
41
+ "summarization": {
42
+ "early_stopping": true,
43
+ "length_penalty": 2.0,
44
+ "max_length": 200,
45
+ "min_length": 30,
46
+ "no_repeat_ngram_size": 3,
47
+ "num_beams": 4,
48
+ "prefix": "summarize: "
49
+ },
50
+ "translation_en_to_de": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to German: "
55
+ },
56
+ "translation_en_to_fr": {
57
+ "early_stopping": true,
58
+ "max_length": 300,
59
+ "num_beams": 4,
60
+ "prefix": "translate English to French: "
61
+ },
62
+ "translation_en_to_ro": {
63
+ "early_stopping": true,
64
+ "max_length": 300,
65
+ "num_beams": 4,
66
+ "prefix": "translate English to Romanian: "
67
+ }
68
+ },
69
+ "torch_dtype": "float16",
70
+ "transformers_version": "4.37.0.dev0",
71
+ "use_cache": true,
72
+ "vocab_size": 32128
73
+ }
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": "4.37.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f8780b3013bf5fbef9ddf565e89b1e1ac3bf2fb8291293a2718e87f468b410
3
+ size 418282136