Hugging Face's logo

optimum-intel-internal-testing
/
tiny-random-zamba2

PyTorch
zamba2
Model card Files
xet
Community
2
rkazants commited on
Commit
0d18fa3
·
verified ·
1 Parent(s): 1f871f6

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +120 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +23 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +44 -0
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_rank": 128,
3
+ "add_bias_linear": false,
4
+ "architectures": [
5
+ "Zamba2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_head_dim": 1,
9
+ "attention_hidden_size": 32,
10
+ "bos_token_id": 1,
11
+ "chunk_size": 256,
12
+ "conv_kernel": 3,
13
+ "d_model": 16,
14
+ "d_state": 32,
15
+ "eos_token_id": 2,
16
+ "expand": 2,
17
+ "hidden_act": "gelu",
18
+ "hidden_size": 16,
19
+ "hybrid_layer_ids": [
20
+ 6,
21
+ 12,
22
+ 18,
23
+ 24,
24
+ 30,
25
+ 36,
26
+ 42,
27
+ 47,
28
+ 51
29
+ ],
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 64,
32
+ "kv_channels": 0,
33
+ "layers_block_type": [
34
+ "mamba",
35
+ "mamba",
36
+ "mamba",
37
+ "mamba",
38
+ "mamba",
39
+ "mamba",
40
+ "hybrid",
41
+ "mamba",
42
+ "mamba",
43
+ "mamba",
44
+ "mamba",
45
+ "mamba",
46
+ "hybrid",
47
+ "mamba",
48
+ "mamba",
49
+ "mamba",
50
+ "mamba",
51
+ "mamba",
52
+ "hybrid",
53
+ "mamba",
54
+ "mamba",
55
+ "mamba",
56
+ "mamba",
57
+ "mamba",
58
+ "hybrid",
59
+ "mamba",
60
+ "mamba",
61
+ "mamba",
62
+ "mamba",
63
+ "mamba",
64
+ "hybrid",
65
+ "mamba",
66
+ "mamba",
67
+ "mamba",
68
+ "mamba",
69
+ "mamba",
70
+ "hybrid",
71
+ "mamba",
72
+ "mamba",
73
+ "mamba",
74
+ "mamba",
75
+ "mamba",
76
+ "hybrid",
77
+ "mamba",
78
+ "mamba",
79
+ "mamba",
80
+ "mamba",
81
+ "hybrid",
82
+ "mamba",
83
+ "mamba",
84
+ "mamba",
85
+ "hybrid",
86
+ "mamba",
87
+ "mamba"
88
+ ],
89
+ "mamba_d_conv": 4,
90
+ "mamba_d_state": 64,
91
+ "mamba_expand": 2,
92
+ "mamba_headdim": 4,
93
+ "mamba_ngroups": 1,
94
+ "max_position_embeddings": 4096,
95
+ "model_type": "zamba2",
96
+ "n_layer": 46,
97
+ "n_mamba_heads": 8,
98
+ "num_attention_heads": 32,
99
+ "num_hidden_layers": 54,
100
+ "num_key_value_heads": 32,
101
+ "num_logits_to_keep": 1,
102
+ "num_mem_blocks": 1,
103
+ "num_query_groups": 32,
104
+ "pad_token_id": 0,
105
+ "rms_norm_eps": 1e-05,
106
+ "rope_theta": 10000,
107
+ "time_step_floor": 0.0001,
108
+ "time_step_limit": null,
109
+ "time_step_max": 0.1,
110
+ "time_step_min": 0.001,
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.49.0",
113
+ "use_cache": true,
114
+ "use_conv_bias": true,
115
+ "use_long_context": false,
116
+ "use_mem_eff_path": false,
117
+ "use_mem_rope": false,
118
+ "use_shared_attention_adapter": false,
119
+ "vocab_size": 50280
120
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.49.0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba10694d9b76fc1f9948b2a6c29042a4a0b9e2a5434fd289b4a284d218fb3c37
3
+ size 5100534
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "extra_special_tokens": {},
36
+ "legacy": true,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": null,
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizerFast",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }