Daoguang commited on
Commit
2bcbeb4
1 Parent(s): 82b9aa1

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "//amlt0a3b8c9fa72c7a7e36e6cd517fb7abe6/data/pycode_func_0214_17M_codepy-110M/model",
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
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 1,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 0,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.12.5",
51
+ "use_cache": true,
52
+ "vocab_size": 32000,
53
+ "window_size": 256
54
+ }
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 sha256:6736e658ccb6f6849ac3a0b5bd756c3ecad8583a1704051d04b19c1020cbd5b3
3
+ size 495109521
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|beginoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|unkoftext|>", "pad_token": "<|padoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|unkoftext|>", "bos_token": "<|beginoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "//amlt0a3b8c9fa72c7a7e36e6cd517fb7abe6/data/pycode_func_0214_17M_codepy-110M/model", "pad_token": "<|padoftext|>", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff