Hugging Face's logo

jonathanjordan21
/
mos-mamba-6x130m-trainer-sft

Text Generation
Transformers
TensorBoard
Safetensors
MoSMamba
conversational
custom_code
Model card Files Metrics Community
jonathanjordan21 commited on
Commit
3ef2e0a
•
1 Parent(s): 6a0aa55

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. config.json +47 -0
  2. model.safetensors +3 -0
  3. runs/Aug30_07-49-54_381fa5904fd3/events.out.tfevents.1725004235.381fa5904fd3.511.0 +3 -0
  4. runs/Aug30_07-53-31_381fa5904fd3/events.out.tfevents.1725004416.381fa5904fd3.511.1 +3 -0
  5. runs/Aug30_07-54-24_381fa5904fd3/events.out.tfevents.1725004473.381fa5904fd3.511.2 +3 -0
  6. runs/Aug30_07-55-24_381fa5904fd3/events.out.tfevents.1725004535.381fa5904fd3.511.3 +3 -0
  7. special_tokens_map.json +30 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +235 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jonathanjordan21/mos-mamba-6x130m-hf",
3
+ "architectures": [
4
+ "MoSMambaForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "jonathanjordan21/mos-mamba-6x130m-hf--configuration_mos_mamba.MoSMambaConfig",
8
+ "AutoModelForCausalLM": "jonathanjordan21/mos-mamba-6x130m-hf--modeling_mos_mamba.MoSMambaForCausalLM"
9
+ },
10
+ "bos_token_id": 0,
11
+ "conv_kernel": 4,
12
+ "d_inner": 1536,
13
+ "d_model": 768,
14
+ "eos_token_id": 50278,
15
+ "expand": 2,
16
+ "fused_add_norm": true,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 768,
19
+ "initializer_range": 0.1,
20
+ "intermediate_size": 1536,
21
+ "layer_norm_epsilon": 1e-05,
22
+ "model_type": "MoSMamba",
23
+ "n_layer": 24,
24
+ "num_hidden_layers": 24,
25
+ "num_selectivities": 6,
26
+ "num_selectivities_per_tok": 2,
27
+ "output_router_logits": true,
28
+ "pad_token_id": 0,
29
+ "pad_vocab_size_multiple": 8,
30
+ "rescale_prenorm_residual": false,
31
+ "residual_in_fp32": true,
32
+ "rms_norm": true,
33
+ "ssm_cfg": {},
34
+ "state_size": 16,
35
+ "time_step_floor": 0.0001,
36
+ "time_step_init_scheme": "random",
37
+ "time_step_max": 0.1,
38
+ "time_step_min": 0.001,
39
+ "time_step_rank": 48,
40
+ "time_step_scale": 1.0,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.42.4",
43
+ "use_bias": false,
44
+ "use_cache": true,
45
+ "use_conv_bias": true,
46
+ "vocab_size": 50280
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532b8658ddf23c63008fd04db13022d169f5270f4b132b73be8bfe1bed9e3a1b
3
+ size 576008736
runs/Aug30_07-49-54_381fa5904fd3/events.out.tfevents.1725004235.381fa5904fd3.511.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47085663b2792d315f325387fa5b6449644b0838d8f55d83edef989eab9a5f79
3
+ size 49408
runs/Aug30_07-53-31_381fa5904fd3/events.out.tfevents.1725004416.381fa5904fd3.511.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5f26009af108729bd79470819209d64d0fdd7dd5994b72c24528d5a0fe92ac
3
+ size 5555
runs/Aug30_07-54-24_381fa5904fd3/events.out.tfevents.1725004473.381fa5904fd3.511.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdddd6793082497e1e5e863bbb0a5ae7088b2bca893115d4e50e507a9962d9d
3
+ size 5762
runs/Aug30_07-55-24_381fa5904fd3/events.out.tfevents.1725004535.381fa5904fd3.511.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb80ee3826acd7f867f88f0c3975f16d4da8a52d70a262f6b445e5e32ceeff4
3
+ size 12486
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "<|im_start|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "50278": {
215
+ "content": "<|im_end|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ }
222
+ },
223
+ "bos_token": "<|endoftext|>",
224
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
225
+ "clean_up_tokenization_spaces": true,
226
+ "eos_token": "<|im_end|>",
227
+ "max_length": 1024,
228
+ "model_max_length": 1000000000000000019884624838656,
229
+ "pad_token": "<|endoftext|>",
230
+ "stride": 0,
231
+ "tokenizer_class": "GPTNeoXTokenizer",
232
+ "truncation_side": "right",
233
+ "truncation_strategy": "longest_first",
234
+ "unk_token": "<|endoftext|>"
235
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4184d158bbf17a47d10f94b14ddb2251d2e6d3c2fa60e2341f33bd4df4cae99b
3
+ size 5304