Hugging Face's logo

Zyphra
/
Zamba2-1.2B-Instruct-v2

Text Generation
Transformers
Safetensors
zamba2
conversational
Model card Files Community
pglo commited on
Commit
749a256
·
verified ·
1 Parent(s): a8ee144

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +97 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +27 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +52 -0
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_rank": 128,
3
+ "add_bias_linear": false,
4
+ "architectures": [
5
+ "Zamba2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_head_dim": 128,
9
+ "attention_hidden_size": 4096,
10
+ "bos_token_id": 1,
11
+ "chunk_size": 256,
12
+ "eos_token_id": 2,
13
+ "ffn_hidden_size": 8192,
14
+ "hidden_act": "gelu",
15
+ "hidden_size": 2048,
16
+ "hybrid_layer_ids": [
17
+ 5,
18
+ 11,
19
+ 17,
20
+ 23,
21
+ 29,
22
+ 35
23
+ ],
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 8192,
26
+ "kv_channels": 64,
27
+ "layers_block_type": [
28
+ "mamba",
29
+ "mamba",
30
+ "mamba",
31
+ "mamba",
32
+ "mamba",
33
+ "hybrid",
34
+ "mamba",
35
+ "mamba",
36
+ "mamba",
37
+ "mamba",
38
+ "mamba",
39
+ "hybrid",
40
+ "mamba",
41
+ "mamba",
42
+ "mamba",
43
+ "mamba",
44
+ "mamba",
45
+ "hybrid",
46
+ "mamba",
47
+ "mamba",
48
+ "mamba",
49
+ "mamba",
50
+ "mamba",
51
+ "hybrid",
52
+ "mamba",
53
+ "mamba",
54
+ "mamba",
55
+ "mamba",
56
+ "mamba",
57
+ "hybrid",
58
+ "mamba",
59
+ "mamba",
60
+ "mamba",
61
+ "mamba",
62
+ "mamba",
63
+ "hybrid",
64
+ "mamba",
65
+ "mamba"
66
+ ],
67
+ "mamba_d_conv": 4,
68
+ "mamba_d_state": 128,
69
+ "mamba_expand": 2,
70
+ "mamba_headdim": 64,
71
+ "mamba_ngroups": 1,
72
+ "max_position_embeddings": 4096,
73
+ "model_type": "zamba2",
74
+ "n_mamba_heads": 64,
75
+ "num_attention_heads": 32,
76
+ "num_hidden_layers": 38,
77
+ "num_key_value_heads": 32,
78
+ "num_logits_to_keep": 1,
79
+ "num_mem_blocks": 1,
80
+ "num_query_groups": 32,
81
+ "pad_token_id": 0,
82
+ "rms_norm_eps": 1e-05,
83
+ "rope_theta": 10000,
84
+ "time_step_floor": 0.0001,
85
+ "time_step_limit": null,
86
+ "time_step_max": 0.1,
87
+ "time_step_min": 0.001,
88
+ "transformers_version": "4.49.0.dev0",
89
+ "use_cache": true,
90
+ "use_conv_bias": true,
91
+ "use_long_context": false,
92
+ "use_mem_eff_path": false,
93
+ "use_mem_rope": true,
94
+ "use_shared_attention_adapter": true,
95
+ "use_shared_mlp_adapter": true,
96
+ "vocab_size": 32000
97
+ }
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.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5101cce10fcb81387d833463e7f1ada6af5084fdffbdd02938c548f2211fc6e6
3
+ size 2430175896
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "[PAD]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "[PAD]",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<|im_start|>",
33
+ "<|im_end|>"
34
+ ],
35
+ "bos_token": "<|im_start|>",
36
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "<|im_end|>",
39
+ "extra_special_tokens": {},
40
+ "legacy": true,
41
+ "max_length": 4096,
42
+ "model_max_length": 4096,
43
+ "pad_token": "[PAD]",
44
+ "sp_model_kwargs": {},
45
+ "spaces_between_special_tokens": false,
46
+ "stride": 0,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "truncation_side": "right",
49
+ "truncation_strategy": "longest_first",
50
+ "unk_token": null,
51
+ "use_default_system_prompt": false
52
+ }