tjellm commited on
Commit
ae1c89d
1 Parent(s): 3757290

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  onnx/directml/Phi-3-mini-4k-instruct-062024-int4/model.onnx.data filter=lfs diff=lfs merge=lfs -text
37
  onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32/model.onnx.data filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  onnx/directml/Phi-3-mini-4k-instruct-062024-int4/model.onnx.data filter=lfs diff=lfs merge=lfs -text
37
  onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32/model.onnx.data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/model.onnx.data filter=lfs diff=lfs merge=lfs -text
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/genai_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 1,
4
+ "context_length": 4096,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": []
9
+ },
10
+ "filename": "model.onnx",
11
+ "head_size": 96,
12
+ "hidden_size": 3072,
13
+ "inputs": {
14
+ "input_ids": "input_ids",
15
+ "attention_mask": "attention_mask",
16
+ "past_key_names": "past_key_values.%d.key",
17
+ "past_value_names": "past_key_values.%d.value"
18
+ },
19
+ "outputs": {
20
+ "logits": "logits",
21
+ "present_key_names": "present.%d.key",
22
+ "present_value_names": "present.%d.value"
23
+ },
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 32,
26
+ "num_key_value_heads": 32
27
+ },
28
+ "eos_token_id": [
29
+ 32000,
30
+ 32001,
31
+ 32007
32
+ ],
33
+ "pad_token_id": 32000,
34
+ "type": "phi3",
35
+ "vocab_size": 32064
36
+ },
37
+ "search": {
38
+ "diversity_penalty": 0.0,
39
+ "do_sample": false,
40
+ "early_stopping": true,
41
+ "length_penalty": 1.0,
42
+ "max_length": 4096,
43
+ "min_length": 0,
44
+ "no_repeat_ngram_size": 0,
45
+ "num_beams": 1,
46
+ "num_return_sequences": 1,
47
+ "past_present_share_buffer": true,
48
+ "repetition_penalty": 1.0,
49
+ "temperature": 1.0,
50
+ "top_k": 1,
51
+ "top_p": 1.0
52
+ }
53
+ }
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b3153df97be2d6ec435e488858fcae9420bb63ee6667ae773e6162b13ac2b85
3
+ size 211703
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798adddc78bdc16a877303e1ceb8938a3cbfe43459c9a6b735a35c9f9babb09c
3
+ size 2722861056
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
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
+ }
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
onnx/cpu_and_mobile/Phi-3-mini-4k-instruct-062024-cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ }
117
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 4096,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
130
+ }