alei97 commited on
Commit
23fca7f
·
verified ·
1 Parent(s): 448f966

Upload FM-6comp-1k model artifacts

Browse files
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/gz66/analog_model/analog_LLM_model_flanT5/flanT5-maskedgen-data6-from-connection-dataaug-noaug-epoch120-dnum1000-search",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "id2label": {
16
+ "0": "LABEL_0"
17
+ },
18
+ "initializer_factor": 1.0,
19
+ "is_encoder_decoder": true,
20
+ "is_gated_act": true,
21
+ "label2id": {
22
+ "LABEL_0": 0
23
+ },
24
+ "layer_norm_epsilon": 1e-06,
25
+ "model_type": "t5",
26
+ "n_positions": 512,
27
+ "num_decoder_layers": 12,
28
+ "num_heads": 12,
29
+ "num_layers": 12,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "regression",
33
+ "relative_attention_max_distance": 128,
34
+ "relative_attention_num_buckets": 32,
35
+ "save_safetensors": false,
36
+ "task_specific_params": {
37
+ "summarization": {
38
+ "early_stopping": true,
39
+ "length_penalty": 2.0,
40
+ "max_length": 200,
41
+ "min_length": 30,
42
+ "no_repeat_ngram_size": 3,
43
+ "num_beams": 4,
44
+ "prefix": "summarize: "
45
+ },
46
+ "translation_en_to_de": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to German: "
51
+ },
52
+ "translation_en_to_fr": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to French: "
57
+ },
58
+ "translation_en_to_ro": {
59
+ "early_stopping": true,
60
+ "max_length": 300,
61
+ "num_beams": 4,
62
+ "prefix": "translate English to Romanian: "
63
+ }
64
+ },
65
+ "tie_word_embeddings": false,
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.49.0",
68
+ "use_cache": false,
69
+ "vocab_size": 32112
70
+ }
data_generated.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "4.49.0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a987e3f535198620534b90f0de01e7d44000e0e202eb2d8995eb249e24574742
3
+ size 990314614