saadalafalcon commited on
Commit
117f113
1 Parent(s): ecd07e0

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aubmindlab/aragpt2-large",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attn_pdrop": 0.1,
9
+ "auto_map": {
10
+ "AutoConfig": "aubmindlab/aragpt2-large--configuration_aragpt2.AraGPT2Config",
11
+ "AutoModel": "aubmindlab/aragpt2-large--modeling_aragpt2.AraGPT2Model",
12
+ "AutoModelForCausalLM": "aubmindlab/aragpt2-large--modeling_aragpt2.AraGPT2LMHeadModel"
13
+ },
14
+ "bos_token_id": 0,
15
+ "embd_pdrop": 0.1,
16
+ "eos_token_id": 0,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "initializer_range": 0.014142135623731,
20
+ "intermediate_size": 5120,
21
+ "layer_norm_epsilon": 1e-05,
22
+ "model_type": "gpt2",
23
+ "n_ctx": 1024,
24
+ "n_embd": 1280,
25
+ "n_head": 20,
26
+ "n_inner": null,
27
+ "n_layer": 36,
28
+ "n_positions": 1024,
29
+ "reorder_and_upcast_attn": false,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_by_inverse_layer_idx": false,
32
+ "scale_attn_weights": true,
33
+ "summary_activation": null,
34
+ "summary_first_dropout": 0.1,
35
+ "summary_proj_to_labels": true,
36
+ "summary_type": "cls_index",
37
+ "summary_use_proj": true,
38
+ "task_specific_params": {
39
+ "text-generation": {
40
+ "do_sample": true,
41
+ "max_length": 50,
42
+ "no_repeat_ngram_size": 3,
43
+ "num_beams": 5,
44
+ "repetition_penalty": 3.0,
45
+ "top_p": 0.95
46
+ }
47
+ },
48
+ "tokenizer_class": "GPT2Tokenizer",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.30.0",
51
+ "use_cache": true,
52
+ "vocab_size": 64000
53
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.30.0"
6
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb3eb6c49b06d0815bd5a4885fa4166507714325ab3ed60af52ae5854352113
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:555376fc23cb4183b31408df4e07d82ab4cbf948ca3cad68385fe573f5942a70
3
+ size 1064
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1306b6c4e63dd564e65e631f5ccb7219f7e31edae748e7c39c019eadb9021f8c
3
+ size 4408