Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +2 -3
- special_tokens_map.json +3 -21
- tokenizer_config.json +31 -25
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
+
}
|
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
-
"
|
4 |
],
|
5 |
"bos_token_id": 1,
|
6 |
"eos_token_id": 2,
|
@@ -9,13 +9,12 @@
|
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 14336,
|
11 |
"max_position_embeddings": 131072,
|
12 |
-
"model_type": "
|
13 |
"num_attention_heads": 32,
|
14 |
"num_hidden_layers": 32,
|
15 |
"num_key_value_heads": 8,
|
16 |
"pretraining_tp": 1,
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
-
"rope_scaling": null,
|
19 |
"rope_theta": 10000.0,
|
20 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
+
"MistralForCausalLM"
|
4 |
],
|
5 |
"bos_token_id": 1,
|
6 |
"eos_token_id": 2,
|
|
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 14336,
|
11 |
"max_position_embeddings": 131072,
|
12 |
+
"model_type": "mistral",
|
13 |
"num_attention_heads": 32,
|
14 |
"num_hidden_layers": 32,
|
15 |
"num_key_value_heads": 8,
|
16 |
"pretraining_tp": 1,
|
17 |
"rms_norm_eps": 1e-05,
|
|
|
18 |
"rope_theta": 10000.0,
|
19 |
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
special_tokens_map.json
CHANGED
@@ -1,23 +1,5 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"unk_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
tokenizer_config.json
CHANGED
@@ -1,36 +1,42 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
},
|
|
|
|
|
12 |
"clean_up_tokenization_spaces": false,
|
13 |
-
"eos_token":
|
14 |
-
|
15 |
-
"content": "</s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": true,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
-
"legacy": null,
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
"pad_token": null,
|
24 |
"sp_model_kwargs": {},
|
25 |
"spaces_between_special_tokens": false,
|
26 |
-
"tokenizer_class": "
|
27 |
-
"unk_token":
|
28 |
-
"__type": "AddedToken",
|
29 |
-
"content": "<unk>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": true,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false
|
34 |
-
},
|
35 |
"use_default_system_prompt": true
|
36 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
"pad_token": null,
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "MistralTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
"use_default_system_prompt": true
|
42 |
}
|