pere commited on
Commit
885d908
1 Parent(s): 17d48a4

first model

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|endoftext|>": 50265}
config.json CHANGED
@@ -1,15 +1,18 @@
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.0,
7
  "bos_token_id": 50256,
 
8
  "embd_pdrop": 0.0,
9
  "eos_token_id": 50256,
10
  "gradient_checkpointing": false,
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
 
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
  "n_embd": 768,
@@ -30,6 +33,7 @@
30
  "max_length": 50
31
  }
32
  },
 
33
  "transformers_version": "4.9.0.dev0",
34
  "use_cache": true,
35
  "vocab_size": 50257
 
1
  {
2
+ "_name_or_path": "norwegian-gpt2",
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,
 
33
  "max_length": 50
34
  }
35
  },
36
+ "torch_dtype": "float32",
37
  "transformers_version": "4.9.0.dev0",
38
  "use_cache": true,
39
  "vocab_size": 50257
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 sha256:269d12af9cbd67b0a184d01059c26b9c096debf65b24ea8e87dc33b6e2656087
3
+ size 510404491
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json CHANGED
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": "norwegian-gpt2", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff