Hugging Face's logo

TitleOS
/
ADBait-1B-FP16

Safetensors
English
granitemoehybrid
android
adb
honeypot
blueteam
Model card Files
xet
 Community
TitleOS commited on
Commit
8e721ad
·
verified ·
1 Parent(s): fc26a44

Upload 6 files

Browse files
Files changed (6) hide show
  1. chat_template.jinja +4 -0
  2. config.json +100 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +14 -0
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteMoeHybridForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_multiplier": 0.0078125,
8
+ "bos_token_id": 100257,
9
+ "dtype": "float16",
10
+ "embedding_multiplier": 12,
11
+ "eos_token_id": 100257,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "init_method": "mup",
15
+ "initializer_range": 0.1,
16
+ "intermediate_size": 4096,
17
+ "layer_types": [
18
+ "mamba",
19
+ "mamba",
20
+ "mamba",
21
+ "mamba",
22
+ "mamba",
23
+ "attention",
24
+ "mamba",
25
+ "mamba",
26
+ "mamba",
27
+ "mamba",
28
+ "mamba",
29
+ "mamba",
30
+ "mamba",
31
+ "mamba",
32
+ "mamba",
33
+ "attention",
34
+ "mamba",
35
+ "mamba",
36
+ "mamba",
37
+ "mamba",
38
+ "mamba",
39
+ "mamba",
40
+ "mamba",
41
+ "mamba",
42
+ "mamba",
43
+ "attention",
44
+ "mamba",
45
+ "mamba",
46
+ "mamba",
47
+ "mamba",
48
+ "mamba",
49
+ "mamba",
50
+ "mamba",
51
+ "mamba",
52
+ "mamba",
53
+ "attention",
54
+ "mamba",
55
+ "mamba",
56
+ "mamba",
57
+ "mamba"
58
+ ],
59
+ "logits_scaling": 6,
60
+ "mamba_chunk_size": 256,
61
+ "mamba_conv_bias": true,
62
+ "mamba_d_conv": 4,
63
+ "mamba_d_head": 64,
64
+ "mamba_d_state": 128,
65
+ "mamba_expand": 2,
66
+ "mamba_n_groups": 1,
67
+ "mamba_n_heads": 48,
68
+ "mamba_proj_bias": false,
69
+ "max_position_embeddings": 131072,
70
+ "model_type": "granitemoehybrid",
71
+ "normalization_function": "rmsnorm",
72
+ "num_attention_heads": 12,
73
+ "num_experts_per_tok": 0,
74
+ "num_hidden_layers": 40,
75
+ "num_key_value_heads": 4,
76
+ "num_local_experts": 0,
77
+ "output_router_logits": false,
78
+ "pad_token_id": 100256,
79
+ "position_embedding_type": "nope",
80
+ "residual_multiplier": 0.22,
81
+ "rms_norm_eps": 1e-05,
82
+ "rope_parameters": {
83
+ "rope_theta": 10000,
84
+ "rope_type": "default"
85
+ },
86
+ "router_aux_loss_coef": 0.01,
87
+ "shared_intermediate_size": 4096,
88
+ "tie_word_embeddings": true,
89
+ "time_step_limit": [
90
+ 0.0,
91
+ {
92
+ "__float__": "Infinity"
93
+ }
94
+ ],
95
+ "time_step_max": 0.1,
96
+ "time_step_min": 0.001,
97
+ "transformers_version": "5.5.4",
98
+ "use_cache": true,
99
+ "vocab_size": 100352
100
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100257,
5
+ "pad_token_id": 100256,
6
+ "transformers_version": "5.5.4"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795835e1ab81df77197e4e80aa18c986d875e980bf7b32923eb8072a682f0b7f
3
+ size 2923128080
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|end_of_text|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|end_of_text|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|pad|>",
11
+ "padding_side": "right",
12
+ "tokenizer_class": "GPT2Tokenizer",
13
+ "unk_token": "<|unk|>"
14
+ }