Hugging Face's logo

lightonai
/
mambaoutai

Text Generation
Transformers
Safetensors
French
English
mamba
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
3
cthiriet commited on
Commit
cf86e12
•
1 Parent(s): beda7be

Add model

Browse files
Files changed (5) hide show
  1. config.json +40 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +16 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +82 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MambaForCausalLM"
4
+ ],
5
+ "d_model": 2688,
6
+ "n_layer": 28,
7
+ "vocab_size": 65024,
8
+ "ssm_cfg": {},
9
+ "rms_norm": true,
10
+ "residual_in_fp32": true,
11
+ "fused_add_norm": true,
12
+ "pad_vocab_size_multiple": 8,
13
+ "pad_token_id": 0,
14
+ "bos_token_id": 1,
15
+ "eos_token_id": 1,
16
+ "conv_kernel": 4,
17
+ "d_inner": 5376,
18
+ "expand": 2,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 2688,
21
+ "initializer_range": 0.1,
22
+ "intermediate_size": 5376,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "mamba",
25
+ "num_hidden_layers": 28,
26
+ "rescale_prenorm_residual": false,
27
+ "state_size": 16,
28
+ "time_step_floor": 0.0001,
29
+ "time_step_init_scheme": "random",
30
+ "time_step_max": 0.1,
31
+ "time_step_min": 0.001,
32
+ "time_step_rank": 168,
33
+ "time_step_scale": 1.0,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.39.0.dev0",
36
+ "use_bias": false,
37
+ "use_cache": true,
38
+ "use_conv_bias": true,
39
+ "tie_word_embeddings": false
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c26fbb55aa6825bea5ce0889ee338e9f1c3a881b96c3fa64f4f65e34df1d16
3
+ size 3244753840
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|pad|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|fim_prefix|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|fim_middle|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|fim_suffix|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<start_system>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<start_user>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<start_assistant>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<end_message>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<start_user>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'system' %}{{ '<start_system>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'assistant' %}{{ '<start_assistant>' + message['content'] + '<end_message>' }}{% else %}{{ raise_exception('Only system, user and assistant roles are supported.') }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<start_assistant>' }}{% endif %}{% endfor %}",
77
+ "bos_token": "<|endoftext|>",
78
+ "clean_up_tokenization_spaces": true,
79
+ "eos_token": "<|endoftext|>",
80
+ "model_max_length": 1000000000000000019884624838656,
81
+ "tokenizer_class": "PreTrainedTokenizerFast"
82
+ }