Hugging Face's logo

yulan-team
/
YuLan-Mini-Instruct-V1

Text Generation
Transformers
PyTorch
English
Chinese
llama
code
math
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
IvanHU commited on
Commit
e185abb
·
1 Parent(s): 9b02111

upload

Browse files
Files changed (6) hide show
  1. config.json +30 -0
  2. generation_config.json +9 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +86 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1920,
12
+ "initializer_range": 5e-05,
13
+ "intermediate_size": 4800,
14
+ "max_position_embeddings": 28723,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 30,
18
+ "num_hidden_layers": 56,
19
+ "num_key_value_heads": 6,
20
+ "pad_token_id": 102,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 490000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.47.0",
28
+ "use_cache": false,
29
+ "vocab_size": 99000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2,
6
+ 106
7
+ ],
8
+ "transformers_version": "4.47.0"
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19ad4da8664b0e3b46a807a24e0b01f99c1f2fa220b56c973d88523c98cf943
3
+ size 4848986274
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "102": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "103": {
39
+ "content": "<reasoning_step>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "104": {
47
+ "content": "<|start_header_id|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "105": {
55
+ "content": "<|end_header_id|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "106": {
63
+ "content": "<|eot_id|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ }
70
+ },
71
+ "bos_token": "<s>",
72
+ "chat_template": "{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"You are YuLan-Mini, created by RUC AI Box. You are a helpful assistant.\" %}\n{%- endif %}\n\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{%- for message in messages %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}",
73
+ "clean_up_tokenization_spaces": false,
74
+ "eos_token": "</s>",
75
+ "extra_special_tokens": {},
76
+ "legacy": true,
77
+ "model_max_length": 1000000000000000019884624838656,
78
+ "pad_token": "<pad>",
79
+ "padding_side": "right",
80
+ "sp_model_kwargs": {},
81
+ "spaces_between_special_tokens": false,
82
+ "split_special_tokens": false,
83
+ "tokenizer_class": "LlamaTokenizer",
84
+ "unk_token": "<unk>",
85
+ "use_default_system_prompt": false
86
+ }