sagorbrur commited on
Commit
86400ac
1 Parent(s): 01ad74c

model files added

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|BOS|>": 50257, "<|PAD|>": 50260, "<|UNK|>": 50259, "<|EOS|>": 50258, "<|SEP|>": 50261}
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "pad_token_id": 50260,
22
+ "predict_special_tokens": true,
23
+ "reorder_and_upcast_attn": false,
24
+ "resid_pdrop": 0.1,
25
+ "scale_attn_by_inverse_layer_idx": false,
26
+ "scale_attn_weights": true,
27
+ "sep_token_id": 50261,
28
+ "summary_activation": null,
29
+ "summary_first_dropout": 0.1,
30
+ "summary_proj_to_labels": true,
31
+ "summary_type": "cls_index",
32
+ "summary_use_proj": true,
33
+ "task_specific_params": {
34
+ "text-generation": {
35
+ "do_sample": true,
36
+ "max_length": 50
37
+ }
38
+ },
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.17.0",
41
+ "use_cache": true,
42
+ "vocab_size": 50262
43
+ }
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:cb6531ff5c7ba8497ec67e69e52217da1cfbc956f44807a65c536a9e2c666a7c
3
+ size 1444602969
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|BOS|>", "eos_token": "<|EOS|>", "unk_token": "<|UNK|>", "sep_token": "<|SEP|>", "pad_token": "<|PAD|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2-medium", "tokenizer_class": "GPT2Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6340bd656c842a347ba65e5cc925755d1522c0bc7f88a17fbc1fb5ca98abce
3
+ size 2991
vocab.json ADDED
The diff for this file is too large to render. See raw diff