Hugging Face's logo

neuralmagic
/
Phi-3-mini-128k-instruct-FP8

Text Generation
Transformers
Safetensors
phi3
fp8
vllm
conversational
custom_code
text-generation-inference
Inference Endpoints
compressed-tensors
Model card Files Community
2
Lin-K76 commited on
Commit
e50dadd
•
1 Parent(s): a3d2552

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. added_tokens.json +13 -0
  2. config.json +147 -0
  3. generation_config.json +11 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. 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 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
11
+ "AutoModelForSequenceClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForSequenceClassification",
12
+ "AutoModelForTokenClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForTokenClassification"
13
+ },
14
+ "bos_token_id": 1,
15
+ "embd_pdrop": 0.0,
16
+ "eos_token_id": 32000,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 3072,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 8192,
21
+ "max_position_embeddings": 131072,
22
+ "model_type": "phi3",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 32,
26
+ "original_max_position_embeddings": 4096,
27
+ "pad_token_id": 32000,
28
+ "quantization_config": {
29
+ "activation_scheme": "static",
30
+ "ignored_layers": [
31
+ "lm_head"
32
+ ],
33
+ "quant_method": "fp8"
34
+ },
35
+ "resid_pdrop": 0.0,
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": {
38
+ "long_factor": [
39
+ 1.0299999713897705,
40
+ 1.0499999523162842,
41
+ 1.0499999523162842,
42
+ 1.0799999237060547,
43
+ 1.2299998998641968,
44
+ 1.2299998998641968,
45
+ 1.2999999523162842,
46
+ 1.4499999284744263,
47
+ 1.5999999046325684,
48
+ 1.6499998569488525,
49
+ 1.8999998569488525,
50
+ 2.859999895095825,
51
+ 3.68999981880188,
52
+ 5.419999599456787,
53
+ 5.489999771118164,
54
+ 5.489999771118164,
55
+ 9.09000015258789,
56
+ 11.579999923706055,
57
+ 15.65999984741211,
58
+ 15.769999504089355,
59
+ 15.789999961853027,
60
+ 18.360000610351562,
61
+ 21.989999771118164,
62
+ 23.079999923706055,
63
+ 30.009998321533203,
64
+ 32.35000228881836,
65
+ 32.590003967285156,
66
+ 35.56000518798828,
67
+ 39.95000457763672,
68
+ 53.840003967285156,
69
+ 56.20000457763672,
70
+ 57.95000457763672,
71
+ 59.29000473022461,
72
+ 59.77000427246094,
73
+ 59.920005798339844,
74
+ 61.190006256103516,
75
+ 61.96000671386719,
76
+ 62.50000762939453,
77
+ 63.3700065612793,
78
+ 63.48000717163086,
79
+ 63.48000717163086,
80
+ 63.66000747680664,
81
+ 63.850006103515625,
82
+ 64.08000946044922,
83
+ 64.760009765625,
84
+ 64.80001068115234,
85
+ 64.81001281738281,
86
+ 64.81001281738281
87
+ ],
88
+ "short_factor": [
89
+ 1.05,
90
+ 1.05,
91
+ 1.05,
92
+ 1.1,
93
+ 1.1,
94
+ 1.1500000000000001,
95
+ 1.2000000000000002,
96
+ 1.2500000000000002,
97
+ 1.3000000000000003,
98
+ 1.3500000000000003,
99
+ 1.5000000000000004,
100
+ 2.000000000000001,
101
+ 2.000000000000001,
102
+ 2.000000000000001,
103
+ 2.000000000000001,
104
+ 2.000000000000001,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.000000000000001,
116
+ 2.000000000000001,
117
+ 2.000000000000001,
118
+ 2.000000000000001,
119
+ 2.000000000000001,
120
+ 2.000000000000001,
121
+ 2.0500000000000007,
122
+ 2.0500000000000007,
123
+ 2.0500000000000007,
124
+ 2.1000000000000005,
125
+ 2.1000000000000005,
126
+ 2.1000000000000005,
127
+ 2.1500000000000004,
128
+ 2.1500000000000004,
129
+ 2.3499999999999996,
130
+ 2.549999999999999,
131
+ 2.5999999999999988,
132
+ 2.5999999999999988,
133
+ 2.7499999999999982,
134
+ 2.849999999999998,
135
+ 2.849999999999998,
136
+ 2.9499999999999975
137
+ ],
138
+ "type": "su"
139
+ },
140
+ "rope_theta": 10000.0,
141
+ "sliding_window": 262144,
142
+ "tie_word_embeddings": false,
143
+ "torch_dtype": "bfloat16",
144
+ "transformers_version": "4.41.2",
145
+ "use_cache": true,
146
+ "vocab_size": 32064
147
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.41.2"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2718c4187eaddf4440876735a2027bf37e7dd432088dcdb12c099cd258cc2a4b
3
+ size 4018329792
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.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": true,
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": "{{ bos_token }}{% 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": 131072,
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
+ }