Hugging Face's logo

GoofyLM
/
BrainrotLM2-Assistant-362M

Text Generation
Transformers
Safetensors
English
llama
Brainrot
art
GenA
conversational
text-generation-inference
Model card Files
xet
Community
FlameF0X commited on
Commit
da9a8d9
·
verified ·
1 Parent(s): 46f9712

Upload 13 files

Browse files
Files changed (13) hide show
  1. config.json +38 -0
  2. generation_config.json +7 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +34 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +155 -0
  11. trainer_state.json +216 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 960,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2560,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 15,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 5,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "float32",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "fp16": "float16",
32
+ "q4f16": "float16"
33
+ }
34
+ },
35
+ "transformers_version": "4.51.3",
36
+ "use_cache": true,
37
+ "vocab_size": 49152
38
+ }
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": 2,
6
+ "transformers_version": "4.51.3"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f2c4a5e2f95070ea789067ffcee980df7a8b467d28a9b201ed2b784f989f45
3
+ size 1447317080
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8ba8e01c178ef6fa98339c2359fb6fe6db898f6ab073664ef04e762d436767
3
+ size 2894813242
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed5c253a48e6001901218a2e9de2ab738bbeb1dc1ea233eaecf6152cbd749c0c
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "extra_special_tokens": {},
150
+ "model_max_length": 8192,
151
+ "pad_token": "<|im_end|>",
152
+ "tokenizer_class": "GPT2Tokenizer",
153
+ "unk_token": "<|endoftext|>",
154
+ "vocab_size": 49152
155
+ }
trainer_state.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.2,
6
+ "eval_steps": 500,
7
+ "global_step": 267,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00749063670411985,
14
+ "grad_norm": 4.558547019958496,
15
+ "learning_rate": 4.831460674157304e-05,
16
+ "loss": 3.2586,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0149812734082397,
21
+ "grad_norm": 4.060137748718262,
22
+ "learning_rate": 4.644194756554308e-05,
23
+ "loss": 2.9414,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.02247191011235955,
28
+ "grad_norm": 4.330236434936523,
29
+ "learning_rate": 4.456928838951311e-05,
30
+ "loss": 2.7364,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0299625468164794,
35
+ "grad_norm": 3.8646533489227295,
36
+ "learning_rate": 4.269662921348315e-05,
37
+ "loss": 2.6617,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03745318352059925,
42
+ "grad_norm": 4.332949161529541,
43
+ "learning_rate": 4.082397003745319e-05,
44
+ "loss": 2.5693,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0449438202247191,
49
+ "grad_norm": 3.7690067291259766,
50
+ "learning_rate": 3.8951310861423226e-05,
51
+ "loss": 2.6648,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.052434456928838954,
56
+ "grad_norm": 3.539844274520874,
57
+ "learning_rate": 3.7078651685393264e-05,
58
+ "loss": 2.6171,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0599250936329588,
63
+ "grad_norm": 4.24369478225708,
64
+ "learning_rate": 3.52059925093633e-05,
65
+ "loss": 2.4795,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.06741573033707865,
70
+ "grad_norm": 4.186371326446533,
71
+ "learning_rate": 3.3333333333333335e-05,
72
+ "loss": 2.6167,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.0749063670411985,
77
+ "grad_norm": 3.6899819374084473,
78
+ "learning_rate": 3.1460674157303374e-05,
79
+ "loss": 2.4597,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.08239700374531835,
84
+ "grad_norm": 4.035410404205322,
85
+ "learning_rate": 2.958801498127341e-05,
86
+ "loss": 2.3755,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0898876404494382,
91
+ "grad_norm": 3.86106538772583,
92
+ "learning_rate": 2.7715355805243448e-05,
93
+ "loss": 2.4617,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.09737827715355805,
98
+ "grad_norm": 5.214311599731445,
99
+ "learning_rate": 2.5842696629213486e-05,
100
+ "loss": 2.3476,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.10486891385767791,
105
+ "grad_norm": 4.270963191986084,
106
+ "learning_rate": 2.3970037453183522e-05,
107
+ "loss": 2.4596,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.11235955056179775,
112
+ "grad_norm": 3.6309258937835693,
113
+ "learning_rate": 2.209737827715356e-05,
114
+ "loss": 2.3118,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.1198501872659176,
119
+ "grad_norm": 3.888986349105835,
120
+ "learning_rate": 2.0224719101123596e-05,
121
+ "loss": 2.3443,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.12734082397003746,
126
+ "grad_norm": 2.937702178955078,
127
+ "learning_rate": 1.8352059925093635e-05,
128
+ "loss": 2.4183,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.1348314606741573,
133
+ "grad_norm": 3.4217689037323,
134
+ "learning_rate": 1.647940074906367e-05,
135
+ "loss": 2.4306,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.14232209737827714,
140
+ "grad_norm": 3.5683271884918213,
141
+ "learning_rate": 1.4606741573033709e-05,
142
+ "loss": 2.3407,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.149812734082397,
147
+ "grad_norm": 3.605642318725586,
148
+ "learning_rate": 1.2734082397003746e-05,
149
+ "loss": 2.3402,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.15730337078651685,
154
+ "grad_norm": 2.3034493923187256,
155
+ "learning_rate": 1.0861423220973783e-05,
156
+ "loss": 2.1756,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.1647940074906367,
161
+ "grad_norm": 3.481696605682373,
162
+ "learning_rate": 8.98876404494382e-06,
163
+ "loss": 2.1487,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.17228464419475656,
168
+ "grad_norm": 3.515986919403076,
169
+ "learning_rate": 7.116104868913858e-06,
170
+ "loss": 2.2253,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.1797752808988764,
175
+ "grad_norm": 3.26123046875,
176
+ "learning_rate": 5.243445692883896e-06,
177
+ "loss": 2.3215,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.18726591760299627,
182
+ "grad_norm": 4.033005714416504,
183
+ "learning_rate": 3.3707865168539327e-06,
184
+ "loss": 2.2975,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1947565543071161,
189
+ "grad_norm": 3.7090864181518555,
190
+ "learning_rate": 1.4981273408239701e-06,
191
+ "loss": 2.2616,
192
+ "step": 260
193
+ }
194
+ ],
195
+ "logging_steps": 10,
196
+ "max_steps": 267,
197
+ "num_input_tokens_seen": 0,
198
+ "num_train_epochs": 1,
199
+ "save_steps": 500,
200
+ "stateful_callbacks": {
201
+ "TrainerControl": {
202
+ "args": {
203
+ "should_epoch_stop": false,
204
+ "should_evaluate": false,
205
+ "should_log": false,
206
+ "should_save": true,
207
+ "should_training_stop": true
208
+ },
209
+ "attributes": {}
210
+ }
211
+ },
212
+ "total_flos": 1032285369139200.0,
213
+ "train_batch_size": 4,
214
+ "trial_name": null,
215
+ "trial_params": null
216
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1ac74783d34e42ccc2da737bfff93ba37dddbb94719fd2396015daa942159ee
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff