Hugging Face's logo

darthhexx
/
Phi-3-medium-128k-instruct-fp8

Text Generation
Transformers
Safetensors
multilingual
phi3
nlp
code
conversational
custom_code
text-generation-inference
Inference Endpoints
fp8
Model card Files Community
2
darthhexx commited on
Commit
8ce426a
•
1 Parent(s): 0c1ed37

Initial commit

Browse files
Files changed (7) hide show
  1. added_tokens.json +13 -0
  2. config.json +174 -0
  3. model.pt +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +130 -0
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
+ }
config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./Phi-3-medium-128k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 5120,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 17920,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 40,
22
+ "num_hidden_layers": 40,
23
+ "num_key_value_heads": 10,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": null,
26
+ "quantization_config": {
27
+ "activation_scheme": "static",
28
+ "quant_method": "fp8"
29
+ },
30
+ "resid_pdrop": 0.0,
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_scaling": {
33
+ "long_factor": [
34
+ 1.0,
35
+ 1.0,
36
+ 1.0,
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ 1.0,
41
+ 1.0,
42
+ 1.0,
43
+ 1.0,
44
+ 1.0,
45
+ 1.0,
46
+ 1.0,
47
+ 1.25,
48
+ 1.25,
49
+ 1.5,
50
+ 2.0,
51
+ 2.75,
52
+ 5.75,
53
+ 5.75,
54
+ 6.5,
55
+ 9.25,
56
+ 11.0,
57
+ 13.25,
58
+ 19.25,
59
+ 19.75,
60
+ 19.75,
61
+ 21.25,
62
+ 21.5,
63
+ 26.5,
64
+ 30.0,
65
+ 33.75,
66
+ 35.25,
67
+ 38.5,
68
+ 42.0,
69
+ 42.25,
70
+ 46.0,
71
+ 47.0,
72
+ 50.0,
73
+ 50.5,
74
+ 51.0,
75
+ 52.0,
76
+ 52.75,
77
+ 53.75,
78
+ 54.75,
79
+ 57.0,
80
+ 57.25,
81
+ 58.5,
82
+ 59.25,
83
+ 59.5,
84
+ 62.0,
85
+ 62.5,
86
+ 62.75,
87
+ 63.25,
88
+ 63.25,
89
+ 63.25,
90
+ 63.75,
91
+ 64.0,
92
+ 64.0,
93
+ 64.25,
94
+ 64.5,
95
+ 64.5,
96
+ 65.0,
97
+ 65.0
98
+ ],
99
+ "short_factor": [
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.01,
107
+ 1.02,
108
+ 1.02,
109
+ 1.04,
110
+ 1.04,
111
+ 1.07,
112
+ 1.07,
113
+ 1.1,
114
+ 1.3000000000000003,
115
+ 1.3000000000000003,
116
+ 1.5000000000000004,
117
+ 1.5700000000000005,
118
+ 1.9000000000000008,
119
+ 2.3100000000000014,
120
+ 2.759999999999992,
121
+ 3.3899999999999784,
122
+ 3.9399999999999666,
123
+ 4.009999999999965,
124
+ 4.289999999999959,
125
+ 4.349999999999958,
126
+ 5.349999999999937,
127
+ 6.659999999999909,
128
+ 7.029999999999901,
129
+ 7.51999999999989,
130
+ 8.00999999999988,
131
+ 8.249999999999876,
132
+ 8.279999999999875,
133
+ 9.629999999999846,
134
+ 9.89999999999984,
135
+ 10.589999999999826,
136
+ 11.049999999999816,
137
+ 11.7899999999998,
138
+ 12.189999999999792,
139
+ 12.889999999999777,
140
+ 13.129999999999772,
141
+ 13.16999999999977,
142
+ 13.20999999999977,
143
+ 13.479999999999764,
144
+ 13.539999999999763,
145
+ 13.779999999999758,
146
+ 13.929999999999755,
147
+ 14.429999999999744,
148
+ 14.759999999999737,
149
+ 15.149999999999729,
150
+ 15.419999999999723,
151
+ 15.53999999999972,
152
+ 15.659999999999718,
153
+ 15.749999999999716,
154
+ 15.759999999999716,
155
+ 15.799999999999715,
156
+ 16.05999999999971,
157
+ 16.079999999999714,
158
+ 16.11999999999972,
159
+ 16.11999999999972,
160
+ 16.18999999999973,
161
+ 16.31999999999975,
162
+ 16.539999999999786,
163
+ 16.799999999999827
164
+ ],
165
+ "type": "su"
166
+ },
167
+ "rope_theta": 10000.0,
168
+ "sliding_window": 131072,
169
+ "tie_word_embeddings": false,
170
+ "torch_dtype": "float16",
171
+ "transformers_version": "4.40.2",
172
+ "use_cache": true,
173
+ "vocab_size": 32064
174
+ }
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8fe8998cdb86545ea89df30c09690545738bcf7d890565cd3a4af1b76bcd7c
3
+ size 14289167090
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
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'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 2048,
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
+ }