Hugging Face's logo

brunosan
/
GPT2-impactscience

Text Generation
Transformers
PyTorch
English
gpt2
climate
Inference Endpoints
text-generation-inference
Model card Files Community
brunosan commited on
Commit
915d446
•
1 Parent(s): eac0a5f

Upload model

Browse files
Files changed (3) hide show
  1. config.json +29 -32
  2. generation_config.json +2 -2
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,42 +1,39 @@
1
  {
2
- "_name_or_path": "xlm-mlm-en-2048",
 
3
  "architectures": [
4
- "XLMWithLMHeadModel"
5
  ],
6
- "asm": false,
7
- "attention_dropout": 0.1,
8
- "bos_index": 0,
9
- "bos_token_id": 0,
10
- "causal": false,
11
- "dropout": 0.1,
12
- "emb_dim": 2048,
13
- "embed_init_std": 0.02209708691207961,
14
- "end_n_top": 5,
15
- "eos_index": 1,
16
- "gelu_activation": true,
17
- "init_std": 0.02,
18
- "is_encoder": true,
19
- "lang_id": 0,
20
- "layer_norm_eps": 1e-12,
21
- "mask_index": 5,
22
- "mask_token_id": 0,
23
- "max_position_embeddings": 512,
24
- "model_type": "xlm",
25
- "n_heads": 16,
26
- "n_langs": 1,
27
- "n_layers": 12,
28
- "pad_index": 2,
29
- "pad_token_id": 2,
30
- "sinusoidal_embeddings": false,
31
- "start_n_top": 5,
32
  "summary_activation": null,
33
  "summary_first_dropout": 0.1,
34
  "summary_proj_to_labels": true,
35
- "summary_type": "first",
36
  "summary_use_proj": true,
 
 
 
 
 
 
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.26.1",
39
- "unk_index": 3,
40
- "use_lang_emb": true,
41
- "vocab_size": 30145
42
  }
 
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
+ "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": "4.26.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
 
39
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "pad_token_id": 2,
5
  "transformers_version": "4.26.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
  "transformers_version": "4.26.1"
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68f58ace83068bb6d5db86425f15d6e0d032a1a83d02f72670f03cdb36380c97
3
- size 2668543605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2b2ced71adfc6ae7e12a9b0ae11d4ad676c384e208f467a3a265e5fc25d9db
3
+ size 510396521