mrm8488 commited on
Commit
031bde9
1 Parent(s): 6d86e83

Initial commit from mrm8488

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|endoftext|>": 50265}
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/spanish-gpt2-rap/checkpoint-9000",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "do_sample": true,
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 50256,
12
+ "gradient_checkpointing": false,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_length": 50,
16
+ "model_type": "gpt2",
17
+ "n_ctx": 1024,
18
+ "n_embd": 768,
19
+ "n_head": 12,
20
+ "n_inner": null,
21
+ "n_layer": 12,
22
+ "n_positions": 1024,
23
+ "pad_token_id": 50265,
24
+ "resid_pdrop": 0.0,
25
+ "scale_attn_weights": true,
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": "4.11.0.dev0",
39
+ "use_cache": true,
40
+ "vocab_size": 50266
41
+ }
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 sha256:1f7abba5c0402485ee3352c52f6a92a2134bce99cfeabf9d6a38fd54bf2b531b
3
+ size 510429033
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
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, "special_tokens_map_file": null, "name_or_path": "/content/drive/MyDrive/spanish-gpt2-rap/checkpoint-9000", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff