kanishka commited on
Commit
56a01b3
1 Parent(s): 5a22430

Training in progress, step 5000

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 16384
3
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/smolm-autoreg-bpe-babylm-seed_1024-1e-3",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 1,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 258,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "prefix": "<s>",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.35.0",
28
+ "use_cache": true,
29
+ "vocab_size": 16384,
30
+ "word_embed_proj_dim": 768
31
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94de30371d23ad346b1b9f316b8e8114fc61237ea80e13ec2a8a1fd5e4d2071
3
+ size 391376736
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "16384": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<|endoftext|>",
38
+ "clean_up_tokenization_spaces": true,
39
+ "eos_token": "<|endoftext|>",
40
+ "max_length": null,
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_to_multiple_of": null,
43
+ "pad_token": "<pad>",
44
+ "pad_token_type_id": 0,
45
+ "padding_side": "right",
46
+ "tokenizer_class": "GPT2Tokenizer",
47
+ "unk_token": "<|endoftext|>"
48
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6db9e358223e9b087921c9f09fc975388850cbb6f6b63996c1da2f1ffcf9842
3
+ size 4728
vocab.json ADDED
The diff for this file is too large to render. See raw diff