aframson commited on
Commit
a018629
1 Parent(s): 5964f6c
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPT2LMHeadModel"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "GPT2Config",
7
+ "AutoModel": "GPT2Model",
8
+ "AutoModelForCausalLM": "GPT2LMHeadModel",
9
+ "AutoModelForQuestionAnswering": "GPT2ForQuestionAnswering"
10
+ },
11
+ "batch_size": 12,
12
+ "block_size": 100,
13
+ "device": "cpu",
14
+ "eval_interval": 250,
15
+ "hidden_dropout_prob": 0.0,
16
+ "hidden_size": 300,
17
+ "learning_rate": 0.001,
18
+ "max_iters": 6000,
19
+ "num_attention_heads": 6,
20
+ "num_hidden_layers": 6,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.33.2",
23
+ "vocab_size": 1000
24
+ }
25
+
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 sha256:6dd1caad31a634aecdf12cc7dd7f814d7345860d8ac624020417b0f085b4e50c
3
+ size 259303146
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1024,
19
+ "pad_token": null,
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff