Jake commited on
Commit
fd12d5d
·
verified ·
1 Parent(s): fbb43d7

Upload SmolLM3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +111 -0
  2. generation_config.json +10 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SmolLM3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128012,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
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
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 65536,
53
+ "max_window_layers": 28,
54
+ "mlp_bias": false,
55
+ "model_type": "smollm3",
56
+ "no_rope_layer_interval": 4,
57
+ "no_rope_layers": [
58
+ 1,
59
+ 1,
60
+ 1,
61
+ 0,
62
+ 1,
63
+ 1,
64
+ 1,
65
+ 0,
66
+ 1,
67
+ 1,
68
+ 1,
69
+ 0,
70
+ 1,
71
+ 1,
72
+ 1,
73
+ 0,
74
+ 1,
75
+ 1,
76
+ 1,
77
+ 0,
78
+ 1,
79
+ 1,
80
+ 1,
81
+ 0,
82
+ 1,
83
+ 1,
84
+ 1,
85
+ 0,
86
+ 1,
87
+ 1,
88
+ 1,
89
+ 0,
90
+ 1,
91
+ 1,
92
+ 1,
93
+ 0
94
+ ],
95
+ "num_attention_heads": 16,
96
+ "num_hidden_layers": 36,
97
+ "num_key_value_heads": 4,
98
+ "pad_token_id": 128012,
99
+ "pretraining_tp": 1,
100
+ "rms_norm_eps": 1e-06,
101
+ "rope_parameters": {
102
+ "rope_theta": 5000000.0,
103
+ "rope_type": "default"
104
+ },
105
+ "sliding_window": null,
106
+ "tie_word_embeddings": true,
107
+ "transformers_version": "5.3.0",
108
+ "use_cache": false,
109
+ "use_sliding_window": false,
110
+ "vocab_size": 128256
111
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 128012
5
+ ],
6
+ "pad_token_id": 128012,
7
+ "temperature": 0.6,
8
+ "top_p": 0.95,
9
+ "transformers_version": "5.3.0"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803ae0a1c18b636e1850b5737289b641aa76287cace6aeff8ef26dd9ddcd3f5c
3
+ size 6150235096