Abo3Adel commited on
Commit
865051d
·
1 Parent(s): fd8cd50

Upload 4 files

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +44 -0
  3. pytorch_model.bin +3 -0
  4. tokenizer.json +0 -0
  5. training_args.bin +0 -0
.gitattributes ADDED
@@ -0,0 +1 @@
 
 
1
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +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": "4.24.0",
42
+ "use_cache": true,
43
+ "vocab_size": 64000
44
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f107c9e232c5a28f94a5141129d9bc71c7c7372a0620aae1c84b1bf393f8653a
3
+ size 552616509
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
Binary file (3.32 kB). View file