Hugging Face's logo

kzipa
/
vikhr-7b-kspitza

TensorBoard
Safetensors
Model card Files Metrics Community
kzipa commited on
Commit
cf47d24
•
1 Parent(s): 76db746

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. adapter_config.json +32 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +16 -0
  4. runs/Jun14_15-37-24_zipa-Z790-Pro-RS-WiFi/events.out.tfevents.1718369076.zipa-Z790-Pro-RS-WiFi.279033.0 +3 -0
  5. special_tokens_map.json +12 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +155 -0
  9. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Vikhrmodels/Vikhr-7B-instruct_0.4",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 128,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 256,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj",
24
+ "up_proj",
25
+ "o_proj",
26
+ "down_proj",
27
+ "gate_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:596138f01250ac9485e8396fb80d4266a997cd7879dea7f7062d7dec1dbd3205
3
+ size 1342239008
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|future_token_0|>": 79085,
3
+ "<|future_token_10|>": 79095,
4
+ "<|future_token_11|>": 79096,
5
+ "<|future_token_1|>": 79086,
6
+ "<|future_token_2|>": 79087,
7
+ "<|future_token_3|>": 79088,
8
+ "<|future_token_4|>": 79089,
9
+ "<|future_token_5|>": 79090,
10
+ "<|future_token_6|>": 79091,
11
+ "<|future_token_7|>": 79092,
12
+ "<|future_token_8|>": 79093,
13
+ "<|future_token_9|>": 79094,
14
+ "<|im_end|>": 79097,
15
+ "<|im_start|>": 79098
16
+ }
runs/Jun14_15-37-24_zipa-Z790-Pro-RS-WiFi/events.out.tfevents.1718369076.zipa-Z790-Pro-RS-WiFi.279033.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f9130460ac5097e1d140a54c506e90ab1ee596c7cd4e4f9388f1fe6e181184
3
+ size 4830
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|im_start|>",
3
+ "eos_token": "<|im_end|>",
4
+ "pad_token": "<|im_end|>",
5
+ "unk_token": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ }
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:e3f0f84b42f79947ab92931c7c5ded699e845e6862e4e29f0b97f87e279da601
3
+ size 1636166
tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "79085": {
30
+ "content": "<|future_token_0|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "79086": {
38
+ "content": "<|future_token_1|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "79087": {
46
+ "content": "<|future_token_2|>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "79088": {
54
+ "content": "<|future_token_3|>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "79089": {
62
+ "content": "<|future_token_4|>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "79090": {
70
+ "content": "<|future_token_5|>",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "79091": {
78
+ "content": "<|future_token_6|>",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "79092": {
86
+ "content": "<|future_token_7|>",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "79093": {
94
+ "content": "<|future_token_8|>",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "79094": {
102
+ "content": "<|future_token_9|>",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "79095": {
110
+ "content": "<|future_token_10|>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "79096": {
118
+ "content": "<|future_token_11|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "79097": {
126
+ "content": "<|im_end|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "79098": {
134
+ "content": "<|im_start|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ }
141
+ },
142
+ "additional_special_tokens": [],
143
+ "bos_token": "<|im_start|>",
144
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
145
+ "clean_up_tokenization_spaces": false,
146
+ "eos_token": "<|im_end|>",
147
+ "legacy": true,
148
+ "model_max_length": 1512,
149
+ "pad_token": "<|im_end|>",
150
+ "sp_model_kwargs": {},
151
+ "spaces_between_special_tokens": false,
152
+ "tokenizer_class": "LlamaTokenizer",
153
+ "unk_token": "<unk>",
154
+ "use_default_system_prompt": true
155
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292a2ef9ffccd8832a5aedae330da15fa813628766654d195dd40455adfeae99
3
+ size 4728