thanhduc1180
commited on
Commit
•
98b64e7
1
Parent(s):
c891070
Training in progress, step 200
Browse files- adapter_config.json +1 -1
- adapter_model.bin +2 -2
- special_tokens_map.json +4 -3
- tokenizer.json +0 -0
- tokenizer_config.json +11 -28
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "vilm/vinallama-7b-chat",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26265c8f1022859fd0a2ac06f980e611beab902cf3c3f1e74220bea9941237f3
|
3 |
+
size 134264202
|
special_tokens_map.json
CHANGED
@@ -2,10 +2,11 @@
|
|
2 |
"additional_special_tokens": [
|
3 |
"<unk>",
|
4 |
"<s>",
|
5 |
-
"</s>"
|
|
|
6 |
],
|
7 |
"bos_token": "<s>",
|
8 |
-
"eos_token": "
|
9 |
-
"pad_token": "
|
10 |
"unk_token": "<unk>"
|
11 |
}
|
|
|
2 |
"additional_special_tokens": [
|
3 |
"<unk>",
|
4 |
"<s>",
|
5 |
+
"</s>",
|
6 |
+
"<|im_end|>"
|
7 |
],
|
8 |
"bos_token": "<s>",
|
9 |
+
"eos_token": "<|im_end|>",
|
10 |
+
"pad_token": "</s>",
|
11 |
"unk_token": "<unk>"
|
12 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -24,32 +24,16 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
-
"special":
|
34 |
-
},
|
35 |
-
"38366": {
|
36 |
-
"content": "<</SYS>>",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": false
|
42 |
-
},
|
43 |
-
"38367": {
|
44 |
-
"content": "[INST]",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": false
|
50 |
},
|
51 |
-
"
|
52 |
-
"content": "
|
53 |
"lstrip": false,
|
54 |
"normalized": false,
|
55 |
"rstrip": false,
|
@@ -60,23 +44,22 @@
|
|
60 |
"additional_special_tokens": [
|
61 |
"<unk>",
|
62 |
"<s>",
|
63 |
-
"</s>"
|
|
|
64 |
],
|
65 |
"bos_token": "<s>",
|
66 |
-
"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 %}",
|
67 |
"clean_up_tokenization_spaces": false,
|
68 |
-
"eos_token": "
|
69 |
-
"legacy":
|
70 |
"max_length": 1024,
|
71 |
"model_max_length": 1000000000000000019884624838656,
|
72 |
-
"pad_token": "
|
73 |
"sp_model_kwargs": {},
|
74 |
-
"spaces_between_special_tokens": false,
|
75 |
"stride": 0,
|
76 |
"tokenizer_class": "LlamaTokenizer",
|
77 |
"truncation_side": "right",
|
78 |
"truncation_strategy": "longest_first",
|
79 |
"unk_token": "<unk>",
|
80 |
-
"use_default_system_prompt":
|
81 |
"use_fast": true
|
82 |
}
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"46303": {
|
28 |
+
"content": "<|im_end|>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
+
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
},
|
35 |
+
"46304": {
|
36 |
+
"content": "<|im_start|>",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
|
|
44 |
"additional_special_tokens": [
|
45 |
"<unk>",
|
46 |
"<s>",
|
47 |
+
"</s>",
|
48 |
+
"<|im_end|>"
|
49 |
],
|
50 |
"bos_token": "<s>",
|
|
|
51 |
"clean_up_tokenization_spaces": false,
|
52 |
+
"eos_token": "<|im_end|>",
|
53 |
+
"legacy": false,
|
54 |
"max_length": 1024,
|
55 |
"model_max_length": 1000000000000000019884624838656,
|
56 |
+
"pad_token": "</s>",
|
57 |
"sp_model_kwargs": {},
|
|
|
58 |
"stride": 0,
|
59 |
"tokenizer_class": "LlamaTokenizer",
|
60 |
"truncation_side": "right",
|
61 |
"truncation_strategy": "longest_first",
|
62 |
"unk_token": "<unk>",
|
63 |
+
"use_default_system_prompt": true,
|
64 |
"use_fast": true
|
65 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0dfc5b24acd4af6b7ddd04bb6f82970de8ccd0d21c99043a23b7909340d3cd0
|
3 |
size 4536
|