Hugging Face's logo

aigdat
/
omost-phi-3-mini-128k_quantized_int4_float16

Safetensors
phi3
custom_code
quark
Model card Files Community
iswaalex commited on
Commit
179fb8a
·
verified ·
1 Parent(s): c4c4580

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. added_tokens.json +13 -0
  2. config.json +205 -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 +132 -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 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lllyasviel/omost-phi-3-mini-128k",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32000,
25
+ "quantization_config": {
26
+ "algo_config": {
27
+ "model_decoder_layers": "model.layers",
28
+ "name": "awq",
29
+ "num_attention_heads": -1,
30
+ "num_key_value_heads": -1,
31
+ "scaling_layers": [
32
+ {
33
+ "inp": "self_attn.qkv_proj",
34
+ "layers": [
35
+ "self_attn.qkv_proj"
36
+ ],
37
+ "module2inspect": "self_attn",
38
+ "prev_op": "input_layernorm"
39
+ },
40
+ {
41
+ "inp": "self_attn.o_proj",
42
+ "layers": [
43
+ "self_attn.o_proj"
44
+ ],
45
+ "prev_op": "self_attn.qkv_proj"
46
+ },
47
+ {
48
+ "inp": "mlp.gate_up_proj",
49
+ "layers": [
50
+ "mlp.gate_up_proj"
51
+ ],
52
+ "module2inspect": "mlp",
53
+ "prev_op": "post_attention_layernorm"
54
+ },
55
+ {
56
+ "inp": "mlp.down_proj",
57
+ "layers": [
58
+ "mlp.down_proj"
59
+ ],
60
+ "prev_op": "mlp.gate_up_proj"
61
+ }
62
+ ]
63
+ },
64
+ "exclude": [],
65
+ "export": {
66
+ "kv_cache_group": [],
67
+ "pack_method": "reorder",
68
+ "weight_format": "real_quantized",
69
+ "weight_merge_groups": null
70
+ },
71
+ "global_quant_config": {
72
+ "bias": null,
73
+ "input_tensors": null,
74
+ "output_tensors": null,
75
+ "target_device": null,
76
+ "weight": {
77
+ "ch_axis": 1,
78
+ "dtype": "uint4",
79
+ "group_size": 128,
80
+ "is_dynamic": false,
81
+ "observer_cls": "PerGroupMinMaxObserver",
82
+ "qscheme": "per_group",
83
+ "round_method": "half_even",
84
+ "scale_type": "float",
85
+ "symmetric": false
86
+ }
87
+ },
88
+ "layer_quant_config": {},
89
+ "layer_type_quant_config": {},
90
+ "quant_method": "quark",
91
+ "quant_mode": "eager_mode"
92
+ },
93
+ "resid_pdrop": 0.0,
94
+ "rms_norm_eps": 1e-05,
95
+ "rope_scaling": {
96
+ "long_factor": [
97
+ 1.0299999713897705,
98
+ 1.0499999523162842,
99
+ 1.0499999523162842,
100
+ 1.0799999237060547,
101
+ 1.2299998998641968,
102
+ 1.2299998998641968,
103
+ 1.2999999523162842,
104
+ 1.4499999284744263,
105
+ 1.5999999046325684,
106
+ 1.6499998569488525,
107
+ 1.8999998569488525,
108
+ 2.859999895095825,
109
+ 3.68999981880188,
110
+ 5.419999599456787,
111
+ 5.489999771118164,
112
+ 5.489999771118164,
113
+ 9.09000015258789,
114
+ 11.579999923706055,
115
+ 15.65999984741211,
116
+ 15.769999504089355,
117
+ 15.789999961853027,
118
+ 18.360000610351562,
119
+ 21.989999771118164,
120
+ 23.079999923706055,
121
+ 30.009998321533203,
122
+ 32.35000228881836,
123
+ 32.590003967285156,
124
+ 35.56000518798828,
125
+ 39.95000457763672,
126
+ 53.840003967285156,
127
+ 56.20000457763672,
128
+ 57.95000457763672,
129
+ 59.29000473022461,
130
+ 59.77000427246094,
131
+ 59.920005798339844,
132
+ 61.190006256103516,
133
+ 61.96000671386719,
134
+ 62.50000762939453,
135
+ 63.3700065612793,
136
+ 63.48000717163086,
137
+ 63.48000717163086,
138
+ 63.66000747680664,
139
+ 63.850006103515625,
140
+ 64.08000946044922,
141
+ 64.760009765625,
142
+ 64.80001068115234,
143
+ 64.81001281738281,
144
+ 64.81001281738281
145
+ ],
146
+ "short_factor": [
147
+ 1.05,
148
+ 1.05,
149
+ 1.05,
150
+ 1.1,
151
+ 1.1,
152
+ 1.1500000000000001,
153
+ 1.2000000000000002,
154
+ 1.2500000000000002,
155
+ 1.3000000000000003,
156
+ 1.3500000000000003,
157
+ 1.5000000000000004,
158
+ 2.000000000000001,
159
+ 2.000000000000001,
160
+ 2.000000000000001,
161
+ 2.000000000000001,
162
+ 2.000000000000001,
163
+ 2.000000000000001,
164
+ 2.000000000000001,
165
+ 2.000000000000001,
166
+ 2.000000000000001,
167
+ 2.000000000000001,
168
+ 2.000000000000001,
169
+ 2.000000000000001,
170
+ 2.000000000000001,
171
+ 2.000000000000001,
172
+ 2.000000000000001,
173
+ 2.000000000000001,
174
+ 2.000000000000001,
175
+ 2.000000000000001,
176
+ 2.000000000000001,
177
+ 2.000000000000001,
178
+ 2.000000000000001,
179
+ 2.0500000000000007,
180
+ 2.0500000000000007,
181
+ 2.0500000000000007,
182
+ 2.1000000000000005,
183
+ 2.1000000000000005,
184
+ 2.1000000000000005,
185
+ 2.1500000000000004,
186
+ 2.1500000000000004,
187
+ 2.3499999999999996,
188
+ 2.549999999999999,
189
+ 2.5999999999999988,
190
+ 2.5999999999999988,
191
+ 2.7499999999999982,
192
+ 2.849999999999998,
193
+ 2.849999999999998,
194
+ 2.9499999999999975
195
+ ],
196
+ "type": "longrope"
197
+ },
198
+ "rope_theta": 10000.0,
199
+ "sliding_window": 262144,
200
+ "tie_word_embeddings": false,
201
+ "torch_dtype": "float16",
202
+ "transformers_version": "4.49.0",
203
+ "use_cache": true,
204
+ "vocab_size": 32064
205
+ }
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": "4.49.0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252509f28f1ae72cc4d9c9b4af8370e96cf1f211150e46f4da4d246c139cd07d
3
+ size 2131346816
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 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": "{{ 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 %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "extra_special_tokens": {},
124
+ "legacy": false,
125
+ "model_max_length": 131072,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "left",
128
+ "sp_model_kwargs": {},
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }