Hugging Face's logo

neuralmagic
/
Phi-3.5-mini-instruct-FP8-KV

Text Generation
Safetensors
phi3
fp8
vllm
conversational
custom_code
compressed-tensors
Model card Files Community
mgoin commited on
Commit
b32b43c
•
1 Parent(s): cc74122

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. added_tokens.json +13 -0
  2. config.json +192 -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 +131 -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 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/af0dfb8029e8a74545d0736d30cb6b58d2f0f3f0",
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
+ "compression_config": {
14
+ "config_groups": {
15
+ "group_0": {
16
+ "input_activations": {
17
+ "actorder": null,
18
+ "block_structure": null,
19
+ "dynamic": false,
20
+ "group_size": null,
21
+ "num_bits": 8,
22
+ "observer": "minmax",
23
+ "observer_kwargs": {},
24
+ "strategy": "tensor",
25
+ "symmetric": true,
26
+ "type": "float"
27
+ },
28
+ "output_activations": null,
29
+ "targets": [
30
+ "Linear"
31
+ ],
32
+ "weights": {
33
+ "actorder": null,
34
+ "block_structure": null,
35
+ "dynamic": false,
36
+ "group_size": null,
37
+ "num_bits": 8,
38
+ "observer": "minmax",
39
+ "observer_kwargs": {},
40
+ "strategy": "tensor",
41
+ "symmetric": true,
42
+ "type": "float"
43
+ }
44
+ }
45
+ },
46
+ "format": "float-quantized",
47
+ "global_compression_ratio": 1.246153835878366,
48
+ "ignore": [
49
+ "lm_head"
50
+ ],
51
+ "kv_cache_scheme": {
52
+ "actorder": null,
53
+ "block_structure": null,
54
+ "dynamic": false,
55
+ "group_size": null,
56
+ "num_bits": 8,
57
+ "observer": "minmax",
58
+ "observer_kwargs": {},
59
+ "strategy": "tensor",
60
+ "symmetric": true,
61
+ "type": "float"
62
+ },
63
+ "quant_method": "compressed-tensors",
64
+ "quantization_status": "compressed",
65
+ "version": "0.6.0.20240927"
66
+ },
67
+ "embd_pdrop": 0.0,
68
+ "eos_token_id": 32000,
69
+ "hidden_act": "silu",
70
+ "hidden_size": 3072,
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 8192,
73
+ "max_position_embeddings": 131072,
74
+ "model_type": "phi3",
75
+ "num_attention_heads": 32,
76
+ "num_hidden_layers": 32,
77
+ "num_key_value_heads": 32,
78
+ "original_max_position_embeddings": 4096,
79
+ "pad_token_id": 32000,
80
+ "resid_pdrop": 0.0,
81
+ "rms_norm_eps": 1e-05,
82
+ "rope_scaling": {
83
+ "long_factor": [
84
+ 1.0800000429153442,
85
+ 1.1100000143051147,
86
+ 1.1399999856948853,
87
+ 1.340000033378601,
88
+ 1.5899999141693115,
89
+ 1.600000023841858,
90
+ 1.6200000047683716,
91
+ 2.620000123977661,
92
+ 3.2300000190734863,
93
+ 3.2300000190734863,
94
+ 4.789999961853027,
95
+ 7.400000095367432,
96
+ 7.700000286102295,
97
+ 9.09000015258789,
98
+ 12.199999809265137,
99
+ 17.670000076293945,
100
+ 24.46000099182129,
101
+ 28.57000160217285,
102
+ 30.420001983642578,
103
+ 30.840002059936523,
104
+ 32.590003967285156,
105
+ 32.93000411987305,
106
+ 42.320003509521484,
107
+ 44.96000289916992,
108
+ 50.340003967285156,
109
+ 50.45000457763672,
110
+ 57.55000305175781,
111
+ 57.93000411987305,
112
+ 58.21000289916992,
113
+ 60.1400032043457,
114
+ 62.61000442504883,
115
+ 62.62000274658203,
116
+ 62.71000289916992,
117
+ 63.1400032043457,
118
+ 63.1400032043457,
119
+ 63.77000427246094,
120
+ 63.93000411987305,
121
+ 63.96000289916992,
122
+ 63.970001220703125,
123
+ 64.02999877929688,
124
+ 64.06999969482422,
125
+ 64.08000183105469,
126
+ 64.12000274658203,
127
+ 64.41000366210938,
128
+ 64.4800033569336,
129
+ 64.51000213623047,
130
+ 64.52999877929688,
131
+ 64.83999633789062
132
+ ],
133
+ "short_factor": [
134
+ 1.0,
135
+ 1.0199999809265137,
136
+ 1.0299999713897705,
137
+ 1.0299999713897705,
138
+ 1.0499999523162842,
139
+ 1.0499999523162842,
140
+ 1.0499999523162842,
141
+ 1.0499999523162842,
142
+ 1.0499999523162842,
143
+ 1.0699999332427979,
144
+ 1.0999999046325684,
145
+ 1.1099998950958252,
146
+ 1.1599998474121094,
147
+ 1.1599998474121094,
148
+ 1.1699998378753662,
149
+ 1.2899998426437378,
150
+ 1.339999794960022,
151
+ 1.679999828338623,
152
+ 1.7899998426437378,
153
+ 1.8199998140335083,
154
+ 1.8499997854232788,
155
+ 1.8799997568130493,
156
+ 1.9099997282028198,
157
+ 1.9399996995925903,
158
+ 1.9899996519088745,
159
+ 2.0199997425079346,
160
+ 2.0199997425079346,
161
+ 2.0199997425079346,
162
+ 2.0199997425079346,
163
+ 2.0199997425079346,
164
+ 2.0199997425079346,
165
+ 2.0299997329711914,
166
+ 2.0299997329711914,
167
+ 2.0299997329711914,
168
+ 2.0299997329711914,
169
+ 2.0299997329711914,
170
+ 2.0299997329711914,
171
+ 2.0299997329711914,
172
+ 2.0299997329711914,
173
+ 2.0299997329711914,
174
+ 2.0799996852874756,
175
+ 2.0899996757507324,
176
+ 2.189999580383301,
177
+ 2.2199995517730713,
178
+ 2.5899994373321533,
179
+ 2.729999542236328,
180
+ 2.749999523162842,
181
+ 2.8399994373321533
182
+ ],
183
+ "type": "longrope"
184
+ },
185
+ "rope_theta": 10000.0,
186
+ "sliding_window": 262144,
187
+ "tie_word_embeddings": false,
188
+ "torch_dtype": "bfloat16",
189
+ "transformers_version": "4.46.0.dev0",
190
+ "use_cache": true,
191
+ "vocab_size": 32064
192
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32007,
6
+ 32001,
7
+ 32000
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.46.0.dev0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052277894809f091bf949b236c940cab6d2a73d3c5509dbe81932cf4c1a98990
3
+ size 4018339544
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 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }