Hugging Face's logo

pytorch
/
SmolLM3-3B-8da4w

Text Generation
PyTorch
Transformers
optimum-executorch
smollm3
executorch
smollm
conversational
torchao
Model card Files
xet
Community
1
guangy10 commited on
Commit
21f1f24
·
verified ·
1 Parent(s): e2ab3a1

Upload SmolLM3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +189 -0
  2. generation_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SmolLM3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128012,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention"
50
+ ],
51
+ "max_position_embeddings": 65536,
52
+ "max_window_layers": 28,
53
+ "mlp_bias": false,
54
+ "model_type": "smollm3",
55
+ "no_rope_layer_interval": 4,
56
+ "no_rope_layers": [
57
+ 1,
58
+ 1,
59
+ 1,
60
+ 0,
61
+ 1,
62
+ 1,
63
+ 1,
64
+ 0,
65
+ 1,
66
+ 1,
67
+ 1,
68
+ 0,
69
+ 1,
70
+ 1,
71
+ 1,
72
+ 0,
73
+ 1,
74
+ 1,
75
+ 1,
76
+ 0,
77
+ 1,
78
+ 1,
79
+ 1,
80
+ 0,
81
+ 1,
82
+ 1,
83
+ 1,
84
+ 0,
85
+ 1,
86
+ 1,
87
+ 1,
88
+ 0,
89
+ 1,
90
+ 1,
91
+ 1,
92
+ 0
93
+ ],
94
+ "num_attention_heads": 16,
95
+ "num_hidden_layers": 36,
96
+ "num_key_value_heads": 4,
97
+ "pad_token_id": 128004,
98
+ "pretraining_tp": 2,
99
+ "quantization_config": {
100
+ "include_input_output_embeddings": false,
101
+ "modules_to_not_convert": [],
102
+ "quant_method": "torchao",
103
+ "quant_type": {
104
+ "default": {
105
+ "_data": {
106
+ "module_fqn_to_config": {
107
+ "_default": {
108
+ "_data": {
109
+ "act_mapping_type": {
110
+ "_data": "ASYMMETRIC",
111
+ "_type": "MappingType"
112
+ },
113
+ "layout": {
114
+ "_data": {},
115
+ "_type": "QDQLayout",
116
+ "_version": 1
117
+ },
118
+ "weight_dtype": {
119
+ "_data": "int4",
120
+ "_type": "torch.dtype"
121
+ },
122
+ "weight_granularity": {
123
+ "_data": {
124
+ "group_size": 32
125
+ },
126
+ "_type": "PerGroup",
127
+ "_version": 1
128
+ },
129
+ "weight_mapping_type": {
130
+ "_data": "SYMMETRIC",
131
+ "_type": "MappingType"
132
+ },
133
+ "weight_scale_dtype": {
134
+ "_data": "bfloat16",
135
+ "_type": "torch.dtype"
136
+ }
137
+ },
138
+ "_type": "Int8DynamicActivationIntxWeightConfig",
139
+ "_version": 1
140
+ },
141
+ "model.embed_tokens": {
142
+ "_data": {
143
+ "granularity": {
144
+ "_data": {
145
+ "axis": 0
146
+ },
147
+ "_type": "PerAxis",
148
+ "_version": 1
149
+ },
150
+ "layout": {
151
+ "_data": {},
152
+ "_type": "QDQLayout",
153
+ "_version": 1
154
+ },
155
+ "mapping_type": {
156
+ "_data": "SYMMETRIC",
157
+ "_type": "MappingType"
158
+ },
159
+ "scale_dtype": null,
160
+ "weight_dtype": {
161
+ "_data": "int8",
162
+ "_type": "torch.dtype"
163
+ }
164
+ },
165
+ "_type": "IntxWeightOnlyConfig",
166
+ "_version": 1
167
+ }
168
+ }
169
+ },
170
+ "_type": "ModuleFqnToConfig",
171
+ "_version": 1
172
+ }
173
+ },
174
+ "quant_type_kwargs": {
175
+ "include_embedding": true
176
+ },
177
+ "untie_embedding_weights": true
178
+ },
179
+ "rms_norm_eps": 1e-06,
180
+ "rope_scaling": null,
181
+ "rope_theta": 5000000.0,
182
+ "sliding_window": null,
183
+ "tie_word_embeddings": false,
184
+ "torch_dtype": "float32",
185
+ "transformers_version": "4.54.0.dev0",
186
+ "use_cache": false,
187
+ "use_sliding_window": false,
188
+ "vocab_size": 128256
189
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128012,
5
+ "pad_token_id": 128004,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.54.0.dev0"
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9601eefbb36ccba63bc467023fc9000b5d0701f9ba28924d9c6c26d0a0a62838
3
+ size 4414829471