Hugging Face's logo

rusticluftig
/
miner2

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
rusticluftig commited on
Commit
02f1b92
·
verified ·
1 Parent(s): bfce360

Upload model

Browse files
Files changed (3) hide show
  1. config.json +33 -38
  2. generation_config.json +2 -5
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,46 +1,41 @@
1
  {
2
- "_name_or_path": "tuanna08go/sn29pre",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
  "architectures": [
6
- "BartForCausalLM"
7
  ],
8
- "attention_dropout": 0.0,
9
- "bos_token_id": 0,
10
- "classifier_dropout": 0.0,
11
- "d_model": 768,
12
- "decoder_attention_heads": 12,
13
- "decoder_ffn_dim": 3072,
14
- "decoder_layerdrop": 0.0,
15
- "decoder_layers": 15,
16
- "decoder_start_token_id": 2,
17
- "dropout": 0.1,
18
- "encoder_attention_heads": 12,
19
- "encoder_ffn_dim": 3072,
20
- "encoder_layerdrop": 0.0,
21
- "encoder_layers": 15,
22
- "eos_token_id": 2,
23
- "forced_eos_token_id": 2,
24
- "id2label": {
25
- "0": "LABEL_0",
26
- "1": "LABEL_1",
27
- "2": "LABEL_2"
 
 
 
 
 
 
 
 
 
28
  },
29
- "init_std": 0.02,
30
- "is_decoder": true,
31
- "is_encoder_decoder": false,
32
- "label2id": {
33
- "LABEL_0": 0,
34
- "LABEL_1": 1,
35
- "LABEL_2": 2
36
- },
37
- "max_position_embeddings": 1024,
38
- "model_type": "bart",
39
- "num_hidden_layers": 15,
40
- "pad_token_id": 1,
41
- "scale_embedding": false,
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.34.1",
44
  "use_cache": true,
45
- "vocab_size": 50265
46
  }
 
1
  {
2
+ "_name_or_path": "gpt2-medium",
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.34.1",
39
  "use_cache": true,
40
+ "vocab_size": 50257
41
  }
generation_config.json CHANGED
@@ -1,9 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
5
- "eos_token_id": 2,
6
- "forced_eos_token_id": 2,
7
- "pad_token_id": 1,
8
  "transformers_version": "4.34.1"
9
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
 
 
 
5
  "transformers_version": "4.34.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ebf53bb5315fd15feaa9635b3ab2543ec53527d14533fee772cb135cc5fc14
3
- size 724724784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe2c3aa64cf154c9c9a9d6349778291668f2bb46751fad3b97857d1fe0e43bc
3
+ size 1419322880