Hugging Face's logo

psyche
/
kogpt

Text Generation
Transformers
PyTorch
Safetensors
English
Korean
gpt2
generation
text-generation-inference
Model card Files
xet
Community
8
psyche commited on
Commit
d5ffe5c
·
1 Parent(s): 6672add

Upload T5ForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +50 -29
  2. generation_config.json +3 -2
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,39 +1,60 @@
1
  {
2
- "_name_or_path": "runs/checkpoint-84000",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 0,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 2,
11
- "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 2048,
15
- "n_embd": 1536,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
19
- "n_positions": 2048,
20
- "reorder_and_upcast_attn": false,
21
- "resid_pdrop": 0.1,
22
- "scale_attn_by_inverse_layer_idx": false,
23
- "scale_attn_weights": true,
24
- "summary_activation": null,
25
- "summary_first_dropout": 0.1,
26
- "summary_proj_to_labels": true,
27
- "summary_type": "cls_index",
28
- "summary_use_proj": true,
29
  "task_specific_params": {
30
- "text-generation": {
31
- "do_sample": true,
32
- "max_length": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  },
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.30.2",
37
  "use_cache": true,
38
- "vocab_size": 32002
39
  }
 
1
  {
2
+ "_name_or_path": "runs/fid_legacy/checkpoint-60408",
 
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
 
27
  "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
  }
55
  },
56
  "torch_dtype": "float32",
57
  "transformers_version": "4.30.2",
58
  "use_cache": true,
59
+ "vocab_size": 32128
60
  }
generation_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "eos_token_id": 2,
 
5
  "transformers_version": "4.30.2"
6
  }
 
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": "4.30.2"
7
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:903e845bdeab5bde239533b3c11c89910b08296838e7d3a32193393537d34625
3
- size 1620115645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6174fe3c21d632e922a498fd5d347893add6efd757af0c3f7c316d9e78040346
3
+ size 891699345