tvergho commited on
Commit
ac210d7
·
1 Parent(s): 9b7d9a9

Model save

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|BOS|>": 50257,
3
+ "<|EOS|>": 50258,
4
+ "<|PAD|>": 50260,
5
+ "<|SEP|>": 50261,
6
+ "<|UNK|>": 50259
7
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 50257,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50258,
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
+ "pad_token_id": 50260,
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
+ "sep_token_id": 50261,
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": "4.26.0",
39
+ "use_cache": true,
40
+ "vocab_size": 50262
41
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.26.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b871b6340c6da1c87856201bcacb464ac48d77cd1ef872647d42723910624f96
3
+ size 510413373
runs/Jan29_19-56-17_c57b82f800e0/1675022190.920735/events.out.tfevents.1675022190.c57b82f800e0.17099.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5fe334922c6ebb3b8fd51bc4ab1dec87263bdfddd8999c4bc7ff95f7bb1272
3
+ size 5671
runs/Jan29_19-56-17_c57b82f800e0/events.out.tfevents.1675022190.c57b82f800e0.17099.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2541265782d93b7325747a2593211b04fc1739079567ce7e98e6cdfc33a4389
3
+ size 40
runs/Jan29_19-57-28_c57b82f800e0/1675022258.5785623/events.out.tfevents.1675022258.c57b82f800e0.17983.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035966123ec00acc3579b525bef08e4e27a3b0f90e0ade082f5ac48668c6434b
3
+ size 5671
runs/Jan29_19-57-28_c57b82f800e0/events.out.tfevents.1675022258.c57b82f800e0.17983.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e30220a765b8fe690cdd1b6dff94aa4248a3864935212a067bce8a4bce7af9
3
+ size 40
runs/Jan29_19-58-30_c57b82f800e0/1675022316.2048283/events.out.tfevents.1675022316.c57b82f800e0.18394.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e663b35cbe5ca5b86e7209e97379cef0457e19f9372ae394bf415a26cadfc158
3
+ size 5671
runs/Jan29_19-58-30_c57b82f800e0/events.out.tfevents.1675022316.c57b82f800e0.18394.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fd13ce1e273efa4f7feee10259b1838b53e60473f1a94fdef52be4bdeca7b0
3
+ size 5530
runs/Jan29_19-58-30_c57b82f800e0/events.out.tfevents.1675022428.c57b82f800e0.18394.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e7b8c1fdd0d6af87da0f9009e0204681a6eb9814dbde542ab4bd57916bdab3a
3
+ size 311
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|BOS|>",
3
+ "eos_token": "<|EOS|>",
4
+ "pad_token": "<|PAD|>",
5
+ "sep_token": "<|SEP|>",
6
+ "unk_token": "<|UNK|>"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4178542ac5e13e0eeffce5bb1ffdec0735fdf919d0fe05b2b98a5a6f73de28ea
3
+ size 3515
vocab.json ADDED
The diff for this file is too large to render. See raw diff