ErazerControl commited on
Commit
106601b
·
verified ·
1 Parent(s): 18cead4

Upload folder using huggingface_hub

Browse files
Phi-3.5-mini-instruct/README.md ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Phi-3.5-mini-instruct
2
+
3
+ ## GenAI WebGPU Model
4
+
5
+ Generated using `onnxruntime_genai.models.builder`
6
+
7
+ - **onnxruntime-genai commit**: `41c4ce18fec1240c2f848725e31fbe8854010188`
8
+ - **transformers version**: `4.57.0`
9
+ - **Precision**: int4
10
+ - **Execution Provider**: webgpu
11
+
12
+ ```
13
+ python -m onnxruntime_genai.models.builder -p int4 -e webgpu -m microsoft/Phi-3.5-mini-instruct -o E:\ai-models\Phi-3.5-mini-instruct\onnx-webgpu\ --extra_options int4_algo_config=rtn_last int4_is_symmetric=true prune_lm_head=true enable_webgpu_graph=true
14
+ ```
15
+
16
+ ## GGUF Model
17
+
18
+ Downloaded from: [MaziyarPanahi/Phi-3.5-mini-instruct-GGUF](https://huggingface.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF)
Phi-3.5-mini-instruct/gguf/Phi-3.5-mini-instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4165e3a71af97f1b4820da61079826d8752a2088e313af0c7d346796c38eff5
3
+ size 2393232672
Phi-3.5-mini-instruct/onnx-webgpu/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
+ }
Phi-3.5-mini-instruct/onnx-webgpu/chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>
2
+ ' + message['content'] + '<|end|>
3
+ '}}{% elif message['role'] == 'user' %}{{'<|user|>
4
+ ' + message['content'] + '<|end|>
5
+ '}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
6
+ ' + message['content'] + '<|end|>
7
+ '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
8
+ ' }}{% else %}{{ eos_token }}{% endif %}
Phi-3.5-mini-instruct/onnx-webgpu/genai_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "webgpu": {
11
+ "enableGraphCapture": "0",
12
+ "validationMode": "disabled",
13
+ "multiRotaryCacheConcatOffset": "4096"
14
+ }
15
+ }
16
+ ]
17
+ },
18
+ "filename": "model.onnx",
19
+ "head_size": 96,
20
+ "hidden_size": 3072,
21
+ "inputs": {
22
+ "input_ids": "input_ids",
23
+ "attention_mask": "attention_mask",
24
+ "past_key_names": "past_key_values.%d.key",
25
+ "past_value_names": "past_key_values.%d.value"
26
+ },
27
+ "outputs": {
28
+ "logits": "logits",
29
+ "present_key_names": "present.%d.key",
30
+ "present_value_names": "present.%d.value"
31
+ },
32
+ "num_attention_heads": 32,
33
+ "num_hidden_layers": 32,
34
+ "num_key_value_heads": 32
35
+ },
36
+ "eos_token_id": [
37
+ 32007,
38
+ 32001,
39
+ 32000
40
+ ],
41
+ "pad_token_id": 32000,
42
+ "type": "phi3",
43
+ "vocab_size": 32064
44
+ },
45
+ "search": {
46
+ "diversity_penalty": 0,
47
+ "do_sample": false,
48
+ "early_stopping": true,
49
+ "length_penalty": 1,
50
+ "max_length": 131072,
51
+ "min_length": 0,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beams": 1,
54
+ "num_return_sequences": 1,
55
+ "past_present_share_buffer": true,
56
+ "repetition_penalty": 1,
57
+ "temperature": 1,
58
+ "top_k": 50,
59
+ "top_p": 1
60
+ }
61
+ }
Phi-3.5-mini-instruct/onnx-webgpu/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08166a117eaaf4a670ea84b930a6ebe771a8964c6ba0f1c91945bede937f6776
3
+ size 240038
Phi-3.5-mini-instruct/onnx-webgpu/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:054fb69e76223380cf1693bde69e1aad2bee6af325b9446f1ae4b1e553ce22f1
3
+ size 2366504960
Phi-3.5-mini-instruct/onnx-webgpu/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
+ }
Phi-3.5-mini-instruct/onnx-webgpu/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Phi-3.5-mini-instruct/onnx-webgpu/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
Phi-3.5-mini-instruct/onnx-webgpu/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
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {},
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
+ }