NetoAI commited on
Commit
12c0633
1 Parent(s): 63e7220

TSLAM-4B Model and config files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NetoAi/Tslam-4B",
3
+ "architectures": [
4
+ "TslamForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 32000,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "llm_int8_enable_fp32_cpu_offload": false,
16
+ "max_position_embeddings": 131072,
17
+ "model_type": "phi3",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 32,
21
+ "original_max_position_embeddings": 4096,
22
+ "pad_token_id": 32000,
23
+ "pretraining_tp": 1,
24
+ "quantization_config": {
25
+ "_load_in_4bit": true,
26
+ "_load_in_8bit": false,
27
+ "bnb_4bit_compute_dtype": "bfloat16",
28
+ "bnb_4bit_quant_storage": "uint8",
29
+ "bnb_4bit_quant_type": "nf4",
30
+ "bnb_4bit_use_double_quant": false,
31
+ "llm_int8_enable_fp32_cpu_offload": false,
32
+ "llm_int8_has_fp16_weight": false,
33
+ "llm_int8_skip_modules": null,
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": true,
36
+ "load_in_8bit": false,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
+ "resid_pdrop": 0.0,
40
+ "rms_norm_eps": 1e-05,
41
+ "rope_scaling": {
42
+ "long_factor": [
43
+ 1.0700000524520874,
44
+ 1.1200000047683716,
45
+ 1.149999976158142,
46
+ 1.4199999570846558,
47
+ 1.5699999332427979,
48
+ 1.7999999523162842,
49
+ 2.129999876022339,
50
+ 2.129999876022339,
51
+ 3.009999990463257,
52
+ 5.910000324249268,
53
+ 6.950000286102295,
54
+ 9.070000648498535,
55
+ 9.930000305175781,
56
+ 10.710000038146973,
57
+ 11.130000114440918,
58
+ 14.609999656677246,
59
+ 15.409998893737793,
60
+ 19.809999465942383,
61
+ 37.279998779296875,
62
+ 38.279998779296875,
63
+ 38.599998474121094,
64
+ 40.12000274658203,
65
+ 46.20000457763672,
66
+ 50.940006256103516,
67
+ 53.66000747680664,
68
+ 54.9373893737793,
69
+ 56.89738845825195,
70
+ 57.28738784790039,
71
+ 59.98738479614258,
72
+ 60.86738586425781,
73
+ 60.887386322021484,
74
+ 61.71739196777344,
75
+ 62.91739273071289,
76
+ 62.957393646240234,
77
+ 63.41739273071289,
78
+ 63.8173942565918,
79
+ 63.83739471435547,
80
+ 63.897396087646484,
81
+ 63.93739700317383,
82
+ 64.06739807128906,
83
+ 64.11434936523438,
84
+ 64.12435150146484,
85
+ 64.15435028076172,
86
+ 64.19435119628906,
87
+ 64.24435424804688,
88
+ 64.57435607910156,
89
+ 64.69000244140625,
90
+ 64.76000213623047
91
+ ],
92
+ "short_factor": [
93
+ 1.1,
94
+ 1.1,
95
+ 1.1,
96
+ 1.3000000000000003,
97
+ 1.3500000000000003,
98
+ 1.3500000000000003,
99
+ 1.4000000000000004,
100
+ 1.5500000000000005,
101
+ 2.000000000000001,
102
+ 2.000000000000001,
103
+ 2.000000000000001,
104
+ 2.000000000000001,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.000000000000001,
116
+ 2.000000000000001,
117
+ 2.000000000000001,
118
+ 2.0500000000000007,
119
+ 2.0500000000000007,
120
+ 2.0500000000000007,
121
+ 2.0500000000000007,
122
+ 2.0500000000000007,
123
+ 2.0500000000000007,
124
+ 2.1000000000000005,
125
+ 2.1000000000000005,
126
+ 2.1500000000000004,
127
+ 2.25,
128
+ 2.25,
129
+ 2.25,
130
+ 2.25,
131
+ 2.25,
132
+ 2.3999999999999995,
133
+ 2.4499999999999993,
134
+ 2.499999999999999,
135
+ 2.6999999999999984,
136
+ 2.6999999999999984,
137
+ 2.7499999999999982,
138
+ 2.799999999999998,
139
+ 2.8999999999999977,
140
+ 3.049999999999997
141
+ ],
142
+ "type": "longrope"
143
+ },
144
+ "rope_theta": 10000.0,
145
+ "sliding_window": 262144,
146
+ "tie_word_embeddings": false,
147
+ "torch_dtype": "float32",
148
+ "transformers_version": "4.45.0.dev0",
149
+ "use_cache": false,
150
+ "vocab_size": 32064
151
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.45.0.dev0"
11
+ }
model-001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce265cd70b8ab8f245d94e5d90aae08c36f66aa63c6b3ba4f9df8d388f17f205
3
+ size 2827324312
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 2048,
125
+ "pad_token": "<unk>",
126
+ "padding_side": "right",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }