Hugging Face's logo

whoisltd
/
my_awesome_qa_model

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
whoisltd commited on
Commit
c5ee27c
•
1 Parent(s): 916a734

End of training

Browse files
Files changed (10) hide show
  1. added_tokens.json +6 -0
  2. config.json +34 -18
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +2 -2
  6. special_tokens_map.json +8 -5
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +6 -10
  9. training_args.bin +1 -1
  10. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 50257,
3
+ "<pad>": 50258,
4
+ "<speaker1>": 50259,
5
+ "<speaker2>": 50260
6
+ }
config.json CHANGED
@@ -1,24 +1,40 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForQuestionAnswering"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
11
  "initializer_range": 0.02,
12
- "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
16
- "pad_token_id": 0,
17
- "qa_dropout": 0.1,
18
- "seq_classif_dropout": 0.2,
19
- "sinusoidal_pos_embds": false,
20
- "tie_weights_": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.31.0",
23
- "vocab_size": 30522
 
24
  }
 
1
  {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
  "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50256,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
  "torch_dtype": "float32",
37
+ "transformers_version": "4.30.2",
38
+ "use_cache": true,
39
+ "vocab_size": 50261
40
  }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.30.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e72813c000fa09405014925ad86286f6a2b475d67a55f3166e79bdd30a83f427
3
- size 265492517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f87cc54746271ce662f71fcff5c5b98f226f8af8c28c1f9715976f3201e3cd8
3
+ size 497819485
special_tokens_map.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
7
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<speaker1>",
4
+ "<speaker2>"
5
+ ],
6
+ "bos_token": "<bos>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<pad>",
9
+ "unk_token": "<|endoftext|>"
10
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,9 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
6
- "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "DistilBertTokenizer",
12
- "unk_token": "[UNK]"
13
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
  "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5ca1b4d973c2788997f0e6d18fbed4531ebc5c7de35a68f67c508156469b506
3
  size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e17327088735b7e0e2ba55f27147f7fbfdda5c8f200e2aee789aedb201b7376
3
  size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff