Hugging Face's logo

md507
/
IORTS-GPT2

Text Generation
Transformers
Safetensors
Arabic
gpt2
Arabic
GPT2
text-generation-inference
Inference Endpoints
Model card Files Community
md507 commited on
Commit
86460ce
·
verified ·
1 Parent(s): 95ad98a

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +44 -44
config.json CHANGED
@@ -1,44 +1,44 @@
1
- {
2
- "_name_or_path": "aubmindlab/aragpt2-base",
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": 0,
11
- "gradient_checkpointing": false,
12
- "initializer_range": 0.02,
13
- "layer_norm_epsilon": 1e-05,
14
- "model_type": "gpt2",
15
- "n_ctx": 1024,
16
- "n_embd": 768,
17
- "n_head": 12,
18
- "n_inner": null,
19
- "n_layer": 12,
20
- "n_positions": 1024,
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
- "no_repeat_ngram_size": 3,
35
- "num_beams": 5,
36
- "repetition_penalty": 3.0,
37
- "top_p": 0.95
38
- }
39
- },
40
- "torch_dtype": "float32",
41
- "transformers_version": "4.47.1",
42
- "use_cache": true,
43
- "vocab_size": 64000
44
- }
 
1
+ {
2
+ "_name_or_path": "aubmindlab/aragpt2-base",
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": 0,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
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
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 5,
36
+ "repetition_penalty": 3.0,
37
+ "top_p": 0.95
38
+ }
39
+ },
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.47.1",
42
+ "use_cache": true,
43
+ "vocab_size": 64000
44
+ }