File size: 5,320 Bytes
8c0145a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
<?xml version="1.0"?>
<net name="Model9" version="11">
	<layers>
		<layer id="0" name="input" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="input">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="self.weight" type="Const" version="opset1">
			<data element_type="i8" shape="151936, 1536" offset="0" size="233373696" />
			<output>
				<port id="0" precision="I8">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="Convert_290867" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="self.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="151936, 1" offset="233373696" size="303872" />
			<output>
				<port id="0" precision="FP16">
					<dim>151936</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="self.weight/fq_weights_0" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>151936</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="self.weight/fq_weights_0/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="aten::embedding/Convert" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="233677568" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="8" name="aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>151936</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="inputs_embeds">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="Result_161867" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1536</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
		<edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
		<edge from-layer="5" from-port="1" to-layer="8" to-port="0" />
		<edge from-layer="6" from-port="1" to-layer="8" to-port="1" />
		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
		<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2025.1.0-17990-dc1d9675cbf" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<nncf>
			<friendly_names_were_updated value="True" />
			<weight_compression>
				<advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}}" />
				<all_layers value="False" />
				<awq value="False" />
				<backup_mode value="int8_asym" />
				<gptq value="False" />
				<group_size value="-1" />
				<ignored_scope value="[]" />
				<lora_correction value="False" />
				<mode value="int8_sym" />
				<ratio value="1.0" />
				<scale_estimation value="False" />
				<sensitivity_metric value="weight_quantization_error" />
			</weight_compression>
		</nncf>
		<optimum>
			<optimum_intel_version value="1.22.0.dev0+753f84d" />
			<optimum_version value="1.24.0.dev0" />
			<pytorch_version value="2.5.0+cpu" />
			<transformers_version value="4.45.0" />
		</optimum>
	</rt_info>
</net>