Upload folder using huggingface_hub
Browse files- config.json +1 -1
- generation_config.json +2 -2
- special_tokens_map.json +23 -0
- tokenizer.json +1 -0
- tokenizer_config.json +30 -23
config.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"rope_theta": 10000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
-
"transformers_version": "4.41.
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 32000
|
29 |
}
|
|
|
23 |
"rope_theta": 10000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.41.1",
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 32000
|
29 |
}
|
generation_config.json
CHANGED
@@ -2,9 +2,9 @@
|
|
2 |
"bos_token_id": 1,
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": 2,
|
|
|
5 |
"pad_token_id": 0,
|
6 |
"temperature": 0.6,
|
7 |
-
"max_length": 4096,
|
8 |
"top_p": 0.9,
|
9 |
-
"transformers_version": "4.
|
10 |
}
|
|
|
2 |
"bos_token_id": 1,
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
"pad_token_id": 0,
|
7 |
"temperature": 0.6,
|
|
|
8 |
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.41.1"
|
10 |
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
CHANGED
@@ -134,6 +134,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
+
"ignore_merges": false,
|
138 |
"vocab": {
|
139 |
"<unk>": 0,
|
140 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,35 +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 |
-
"__type": "AddedToken",
|
15 |
-
"content": "</s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
"legacy": false,
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
"pad_token": null,
|
24 |
"padding_side": "right",
|
25 |
"sp_model_kwargs": {},
|
26 |
"tokenizer_class": "LlamaTokenizer",
|
27 |
-
"unk_token":
|
28 |
-
|
29 |
-
"content": "<unk>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false
|
34 |
-
}
|
35 |
}
|
|
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
"legacy": false,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
"pad_token": null,
|
37 |
"padding_side": "right",
|
38 |
"sp_model_kwargs": {},
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|