ZeyuMax commited on
Commit
df7e390
·
1 Parent(s): 8fcd91b

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roneneldan/TinyStories-33M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local"
13
+ ],
14
+ "attention_types": [
15
+ [
16
+ [
17
+ "global",
18
+ "local"
19
+ ],
20
+ 2
21
+ ]
22
+ ],
23
+ "bos_token_id": 50256,
24
+ "classifier_dropout": 0.1,
25
+ "embed_dropout": 0,
26
+ "eos_token_id": 50256,
27
+ "gradient_checkpointing": false,
28
+ "hidden_size": 768,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": null,
31
+ "layer_norm_epsilon": 1e-05,
32
+ "max_position_embeddings": 2048,
33
+ "model_type": "gpt_neo",
34
+ "num_heads": 16,
35
+ "num_layers": 4,
36
+ "quantization_config": {
37
+ "batch_size": 1,
38
+ "bits": 4,
39
+ "block_name_to_quantize": null,
40
+ "cache_block_outputs": true,
41
+ "damp_percent": 0.1,
42
+ "dataset": "c4",
43
+ "desc_act": false,
44
+ "exllama_config": {
45
+ "version": 1
46
+ },
47
+ "group_size": 128,
48
+ "max_input_length": null,
49
+ "model_seqlen": null,
50
+ "module_name_preceding_first_block": null,
51
+ "modules_in_block_to_quantize": null,
52
+ "pad_token_id": null,
53
+ "quant_method": "gptq",
54
+ "sym": true,
55
+ "tokenizer": null,
56
+ "true_sequential": true,
57
+ "use_cuda_fp16": false,
58
+ "use_exllama": true
59
+ },
60
+ "resid_dropout": 0,
61
+ "summary_activation": null,
62
+ "summary_first_dropout": 0.1,
63
+ "summary_proj_to_labels": true,
64
+ "summary_type": "cls_index",
65
+ "summary_use_proj": true,
66
+ "torch_dtype": "float16",
67
+ "transformers_version": "4.37.0.dev0",
68
+ "use_cache": true,
69
+ "vocab_size": 50257,
70
+ "window_size": 256
71
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.37.0.dev0"
6
+ }
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 sha256:9b10808f9236907a9f1fe6a4650d1715c7a8cd34de24c2a61358545d287c6a29
3
+ size 95257664
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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": 2048,
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