Upload 6 files
Browse files- config.json +29 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +123 -0
- tokenizer_config.json +66 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 512,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 2048,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"n_positions": 512,
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 8,
|
18 |
+
"num_key_value_heads": 16,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.38.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_flash_attention_2": true,
|
28 |
+
"vocab_size": 22
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.38.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e045269ba3b827709b0a3f49220c429ecb0dd668668780fd18185d1c230accaf
|
3 |
+
size 125962208
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|bos|>",
|
3 |
+
"eos_token": "<|eos|>",
|
4 |
+
"pad_token": "<|pad|>"
|
5 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<|pad|>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "<|bos|>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "<|eos|>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "<|tag_start|>",
|
36 |
+
"single_word": true,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": false
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "<|tag_end|>",
|
45 |
+
"single_word": true,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 5,
|
53 |
+
"content": "<|5|>",
|
54 |
+
"single_word": true,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 6,
|
62 |
+
"content": "<|3|>",
|
63 |
+
"single_word": true,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"normalized": false,
|
67 |
+
"special": false
|
68 |
+
}
|
69 |
+
],
|
70 |
+
"normalizer": null,
|
71 |
+
"pre_tokenizer": {
|
72 |
+
"type": "ByteLevel",
|
73 |
+
"add_prefix_space": false,
|
74 |
+
"trim_offsets": true,
|
75 |
+
"use_regex": true
|
76 |
+
},
|
77 |
+
"post_processor": {
|
78 |
+
"type": "ByteLevel",
|
79 |
+
"add_prefix_space": true,
|
80 |
+
"trim_offsets": true,
|
81 |
+
"use_regex": true
|
82 |
+
},
|
83 |
+
"decoder": {
|
84 |
+
"type": "ByteLevel",
|
85 |
+
"add_prefix_space": true,
|
86 |
+
"trim_offsets": true,
|
87 |
+
"use_regex": true
|
88 |
+
},
|
89 |
+
"model": {
|
90 |
+
"type": "BPE",
|
91 |
+
"dropout": null,
|
92 |
+
"unk_token": null,
|
93 |
+
"continuing_subword_prefix": null,
|
94 |
+
"end_of_word_suffix": null,
|
95 |
+
"fuse_unk": false,
|
96 |
+
"byte_fallback": false,
|
97 |
+
"vocab": {
|
98 |
+
"<|pad|>": 0,
|
99 |
+
"<|bos|>": 1,
|
100 |
+
"<|eos|>": 2,
|
101 |
+
"<|tag_start|>": 3,
|
102 |
+
"<|tag_end|>": 4,
|
103 |
+
"<|5|>": 5,
|
104 |
+
"<|3|>": 6,
|
105 |
+
"0": 7,
|
106 |
+
"1": 8,
|
107 |
+
"2": 9,
|
108 |
+
"3": 10,
|
109 |
+
"4": 11,
|
110 |
+
"5": 12,
|
111 |
+
"6": 13,
|
112 |
+
"7": 14,
|
113 |
+
"8": 15,
|
114 |
+
"9": 16,
|
115 |
+
"A": 17,
|
116 |
+
"T": 18,
|
117 |
+
"C": 19,
|
118 |
+
"G": 20,
|
119 |
+
"N": 21
|
120 |
+
},
|
121 |
+
"merges": []
|
122 |
+
}
|
123 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<|pad|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<|bos|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<|eos|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<|tag_start|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": true,
|
33 |
+
"special": false
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "<|tag_end|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": true,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<|5|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": true,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "<|3|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": true,
|
57 |
+
"special": false
|
58 |
+
}
|
59 |
+
},
|
60 |
+
"bos_token": "<|bos|>",
|
61 |
+
"clean_up_tokenization_spaces": true,
|
62 |
+
"eos_token": "<|eos|>",
|
63 |
+
"model_max_length": 1000000000000000019884624838656,
|
64 |
+
"pad_token": "<|pad|>",
|
65 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
66 |
+
}
|