keshan commited on
Commit
f42b10e
1 Parent(s): 926e408

adding pytorch and tf models

Browse files

added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"<|endoftext|>": 50265}
config.json CHANGED
@@ -1,7 +1,8 @@
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
- "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.0,
7
  "bos_token_id": 50256,
@@ -30,6 +31,7 @@
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": "Sinhala-gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPT2Model"
6
  ],
7
  "attn_pdrop": 0.0,
8
  "bos_token_id": 50256,
31
  "max_length": 50
32
  }
33
  },
34
+ "torch_dtype": "float32",
35
  "transformers_version": "4.9.0.dev0",
36
  "use_cache": true,
37
  "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 sha256:9bafaac895bfbfe9ab7bf5c70dd9b60f68642ffafd85b74845fa3ab4f391818f
3
+ size 510397417
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de856eee531adc79d97b05f67016c31f5c253717c8cc21bcc717a3e6fa975c90
3
+ size 497934920
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": "Sinhala-gpt2", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff