blueapple8259
commited on
Commit
•
270feb5
1
Parent(s):
7d2f9f8
Upload 8 files
Browse files- config.json +47 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +33 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "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 |
+
],
|
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 |
+
"resid_dropout": 0,
|
37 |
+
"summary_activation": null,
|
38 |
+
"summary_first_dropout": 0.1,
|
39 |
+
"summary_proj_to_labels": true,
|
40 |
+
"summary_type": "cls_index",
|
41 |
+
"summary_use_proj": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.31.0",
|
44 |
+
"use_cache": false,
|
45 |
+
"vocab_size": 50257,
|
46 |
+
"window_size": 256
|
47 |
+
}
|
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:a5fdeb3bfc3da3895091880c1ee94c9fa60fe695b942b75b113dea95088cf08f
|
3 |
+
size 274061336
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13db4fc13b83bfb86ff0fbb28b175dad0f1943991768043a35706585d316788c
|
3 |
+
size 274074966
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 2048,
|
23 |
+
"pad_token": null,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|