suayptalha commited on
Commit
af031f8
·
verified ·
1 Parent(s): 708f566

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "suayptalha/mingru-lm3",
3
+ "architectures": [
4
+ "MinGRULMForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "suayptalha/minGRU-LM--configuration_minGRULM.MinGRULMConfig",
8
+ "AutoModelForCausalLM": "suayptalha/minGRU-LM--modeling_minGRULM.MinGRULMForCausalLM"
9
+ },
10
+ "bos_token_id": 0,
11
+ "d_model": 512,
12
+ "depth": 12,
13
+ "dim": 512,
14
+ "enable_conv": false,
15
+ "eos_token_id": 0,
16
+ "expand": 2.0,
17
+ "ff_mult": 4,
18
+ "initializer_range": 0.02,
19
+ "min_gru_expansion": 1.5,
20
+ "model_type": "mingru",
21
+ "n_layer": 12,
22
+ "num_tokens": 50257,
23
+ "pad_token_id": 0,
24
+ "pad_vocab_size_multiple": 8,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.44.2",
27
+ "vocab_size": 50257
28
+ }
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 sha256:81320a252afc47def788c4bd14ee3e3ac53c01eab65024b15711666854cf30bf
3
+ size 363350103
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "max_length": 128,
20
+ "model_max_length": 1024,
21
+ "pad_to_multiple_of": null,
22
+ "pad_token": "<|endoftext|>",
23
+ "pad_token_type_id": 0,
24
+ "padding_side": "right",
25
+ "stride": 0,
26
+ "tokenizer_class": "GPT2Tokenizer",
27
+ "truncation_side": "right",
28
+ "truncation_strategy": "longest_first",
29
+ "unk_token": "<|endoftext|>"
30
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff