jojo1899 commited on
Commit
86ce7f4
1 Parent(s): e45c15f

Initial commit

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model.onnx.data filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,17 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
4
+
5
+ This is an INT4 quantized version of the `Phi-3.5-mini-instruct` model. The Python packages used in creating this model are as follows:
6
+ ```
7
+ onnx==1.16.1
8
+ onnxruntime-directml==1.20.0
9
+ onnxruntime-genai-directml==0.4.0
10
+ torch==2.5.1
11
+ transformers==4.45.2
12
+ ```
13
+ This quantized model is created using the following command:
14
+ ```
15
+ python -m onnxruntime_genai.models.builder -m microsoft/Phi-3.5-mini-instruct -e dml -p int4 --extra_options {"int4_block_size"=128} -o ./Phi-3.5-mini-instruct_onnx_int4
16
+ ```
17
+ `onnxruntime_genai.models.builder` quantizes the model using `MatMul4BitsQuantizer` from `matmul_4bits_quantizer.py` of `onnxruntime/quantization/` with the `"DEFAULT"` method.
genai_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 1,
4
+ "context_length": 131072,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "dml": {}
11
+ }
12
+ ]
13
+ },
14
+ "filename": "model.onnx",
15
+ "head_size": 96,
16
+ "hidden_size": 3072,
17
+ "inputs": {
18
+ "input_ids": "input_ids",
19
+ "attention_mask": "attention_mask",
20
+ "position_ids": "position_ids",
21
+ "past_key_names": "past_key_values.%d.key",
22
+ "past_value_names": "past_key_values.%d.value"
23
+ },
24
+ "outputs": {
25
+ "logits": "logits",
26
+ "present_key_names": "present.%d.key",
27
+ "present_value_names": "present.%d.value"
28
+ },
29
+ "num_attention_heads": 32,
30
+ "num_hidden_layers": 32,
31
+ "num_key_value_heads": 32
32
+ },
33
+ "eos_token_id": [
34
+ 32007,
35
+ 32001,
36
+ 32000
37
+ ],
38
+ "pad_token_id": 32000,
39
+ "type": "phi3",
40
+ "vocab_size": 32064
41
+ },
42
+ "search": {
43
+ "diversity_penalty": 0.0,
44
+ "do_sample": false,
45
+ "early_stopping": true,
46
+ "length_penalty": 1.0,
47
+ "max_length": 131072,
48
+ "min_length": 0,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beams": 1,
51
+ "num_return_sequences": 1,
52
+ "past_present_share_buffer": true,
53
+ "repetition_penalty": 1.0,
54
+ "temperature": 1.0,
55
+ "top_k": 1,
56
+ "top_p": 1.0
57
+ }
58
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e054c579515f9f69dc692f31b9c72b0b3b2cae6eb0c2f78c0bd91773a14dc3ca
3
+ size 277869
model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b05666c2522dc24b1d711914dea564ca4f897a6f4120e3f63f75dcd7fe236ab
3
+ size 2316404736
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|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 %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 131072,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }