lianmingjie
commited on
Commit
•
3aac83a
1
Parent(s):
8789b67
new json file
Browse files- added_tokens.json +5 -0
- config.json +2 -1
- generation_config.json +4 -4
- model.safetensors.index.json +0 -0
- special_tokens_map.json +20 -0
- tokenizer.json +1 -0
- tokenizer_config.json +6 -2
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
@@ -20,7 +21,7 @@
|
|
20 |
"sliding_window": 131072,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
-
"transformers_version": "4.
|
24 |
"use_cache": true,
|
25 |
"use_sliding_window": false,
|
26 |
"vocab_size": 152064
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/workspace/models/Qwen2-72B-Instruct",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
|
|
21 |
"sliding_window": 131072,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.41.2",
|
25 |
"use_cache": true,
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 152064
|
generation_config.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"bos_token_id": 151643,
|
3 |
-
"pad_token_id": 151643,
|
4 |
"do_sample": true,
|
5 |
"eos_token_id": [
|
6 |
151645,
|
7 |
151643
|
8 |
],
|
|
|
9 |
"repetition_penalty": 1.05,
|
10 |
"temperature": 0.7,
|
11 |
-
"top_p": 0.8,
|
12 |
"top_k": 20,
|
13 |
-
"
|
14 |
-
|
|
|
|
1 |
{
|
2 |
"bos_token_id": 151643,
|
|
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
151645,
|
6 |
151643
|
7 |
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
"repetition_penalty": 1.05,
|
10 |
"temperature": 0.7,
|
|
|
11 |
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.41.2"
|
14 |
+
}
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
CHANGED
@@ -73,6 +73,7 @@
|
|
73 |
"end_of_word_suffix": "",
|
74 |
"fuse_unk": false,
|
75 |
"byte_fallback": false,
|
|
|
76 |
"vocab": {
|
77 |
"!": 0,
|
78 |
"\"": 1,
|
|
|
73 |
"end_of_word_suffix": "",
|
74 |
"fuse_unk": false,
|
75 |
"byte_fallback": false,
|
76 |
+
"ignore_merges": false,
|
77 |
"vocab": {
|
78 |
"!": 0,
|
79 |
"\"": 1,
|
tokenizer_config.json
CHANGED
@@ -26,14 +26,18 @@
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
30 |
"bos_token": null,
|
31 |
-
"chat_template": "{%
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "<|im_end|>",
|
34 |
"errors": "replace",
|
35 |
"model_max_length": 131072,
|
36 |
"pad_token": "<|endoftext|>",
|
|
|
37 |
"split_special_tokens": false,
|
38 |
"tokenizer_class": "Qwen2Tokenizer",
|
39 |
"unk_token": null
|
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
"bos_token": null,
|
34 |
+
"chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
"eos_token": "<|im_end|>",
|
37 |
"errors": "replace",
|
38 |
"model_max_length": 131072,
|
39 |
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "left",
|
41 |
"split_special_tokens": false,
|
42 |
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
"unk_token": null
|