Upload 6 files
Browse filesFist part of files.
- added_tokens.json +4 -0
- mlc-chat-config.json +23 -0
- ndarray-cache.json +0 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|end_of_turn|>": 32000,
|
3 |
+
"<|pad_0|>": 32001
|
4 |
+
}
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_lib": "openchat_3.5-q4f16_1",
|
3 |
+
"local_id": "openchat_3.5-q4f16_1",
|
4 |
+
"conv_template": "mistral_default",
|
5 |
+
"temperature": 0.7,
|
6 |
+
"repetition_penalty": 1.0,
|
7 |
+
"top_p": 0.95,
|
8 |
+
"mean_gen_len": 128,
|
9 |
+
"max_gen_len": 16384,
|
10 |
+
"num_shards": 1,
|
11 |
+
"use_presharded_weights": false,
|
12 |
+
"shift_fill_factor": 0.3,
|
13 |
+
"tokenizer_files": [
|
14 |
+
"added_tokens.json",
|
15 |
+
"tokenizer.json",
|
16 |
+
"tokenizer.model"
|
17 |
+
],
|
18 |
+
"model_category": "mistral",
|
19 |
+
"model_name": "openchat_3.5",
|
20 |
+
"vocab_size": 32002,
|
21 |
+
"prefill_chunk_size": 4096,
|
22 |
+
"sliding_window": 4096
|
23 |
+
}
|
ndarray-cache.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"32000": {
|
30 |
+
"content": "<|end_of_turn|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|pad_0|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"additional_special_tokens": [
|
47 |
+
"<|end_of_turn|>",
|
48 |
+
"<|pad_0|>"
|
49 |
+
],
|
50 |
+
"bos_token": "<s>",
|
51 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
|
52 |
+
"clean_up_tokenization_spaces": false,
|
53 |
+
"eos_token": "<|end_of_turn|>",
|
54 |
+
"legacy": true,
|
55 |
+
"model_max_length": 1000000000000000019884624838656,
|
56 |
+
"pad_token": null,
|
57 |
+
"sp_model_kwargs": {},
|
58 |
+
"spaces_between_special_tokens": false,
|
59 |
+
"tokenizer_class": "LlamaTokenizer",
|
60 |
+
"unk_token": "<unk>",
|
61 |
+
"use_default_system_prompt": true
|
62 |
+
}
|