vagrawal commited on
Commit
e5e7525
·
verified ·
1 Parent(s): 39fcd7b

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_type": "relu",
3
+ "alibi": false,
4
+ "alibi_bias_max": 8.0,
5
+ "architectures": [
6
+ "OLMoForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_layer_norm": false,
10
+ "attention_layer_norm_with_affine": false,
11
+ "attn_lora_proj_dim": null,
12
+ "bias_for_layer_norm": false,
13
+ "block_group_size": 1,
14
+ "block_type": "ngpt_att_only",
15
+ "clip_qkv": null,
16
+ "d_model": 2048,
17
+ "emb_init_std": null,
18
+ "embedding_dropout": 0.0,
19
+ "embedding_layer_norm": false,
20
+ "embedding_size": 100352,
21
+ "eos_token_id": 100257,
22
+ "flash_attention": true,
23
+ "head_dim": null,
24
+ "head_dim_qk": null,
25
+ "include_bias": false,
26
+ "init_cutoff_factor": null,
27
+ "init_device": "meta",
28
+ "init_fn": "mitchell",
29
+ "init_std": 0.02,
30
+ "layer_norm_eps": 1e-05,
31
+ "layer_norm_type": "rms",
32
+ "layer_norm_with_affine": false,
33
+ "max_sequence_length": 4096,
34
+ "mlp_hidden_size": null,
35
+ "mlp_ratio": 1,
36
+ "model_type": "hf_olmo",
37
+ "multi_query_attention": null,
38
+ "n_heads": 16,
39
+ "n_heads_mlp": 16,
40
+ "n_kv_heads": null,
41
+ "n_layers": 16,
42
+ "norm_after": false,
43
+ "pad_token_id": 100277,
44
+ "precision": "amp_bf16",
45
+ "residual_dropout": 0.0,
46
+ "rope": true,
47
+ "rope_full_precision": true,
48
+ "rope_theta": 10000,
49
+ "scale_emb_init": false,
50
+ "scale_logits": false,
51
+ "transformers_version": "4.57.0",
52
+ "use_cache": true,
53
+ "vocab_size": 100278,
54
+ "weight_tying": false
55
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b98e272aa7965d5ef015a0952e799a1d82e6f3bcbc909d89c9e1d63eb7b660a7
3
+ size 5940253491
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "eos_token": "<|endoftext|>",
3
+ "pad_token": "<|pad|>"
4
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "100256": {
4
+ "content": "<|extra_id_0|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "100257": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "100258": {
20
+ "content": "<|fim_prefix|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100259": {
28
+ "content": "<|fim_middle|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "100260": {
36
+ "content": "<|fim_suffix|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "100261": {
44
+ "content": "|||PHONE_NUMBER|||",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "100262": {
52
+ "content": "|||EMAIL_ADDRESS|||",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "100263": {
60
+ "content": "|||IP_ADDRESS|||",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "100264": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "100265": {
76
+ "content": "<|im_end|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "100266": {
84
+ "content": "<|extra_id_1|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "100267": {
92
+ "content": "<|extra_id_2|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "100268": {
100
+ "content": "<|extra_id_3|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "100269": {
108
+ "content": "<|extra_id_4|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "100270": {
116
+ "content": "<|extra_id_5|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "100271": {
124
+ "content": "<|extra_id_6|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "100272": {
132
+ "content": "<|extra_id_7|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "100273": {
140
+ "content": "<|extra_id_8|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "100274": {
148
+ "content": "<|extra_id_9|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "100275": {
156
+ "content": "<|extra_id_10|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "100276": {
164
+ "content": "<|endofprompt|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "100277": {
172
+ "content": "<|pad|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ }
179
+ },
180
+ "clean_up_tokenization_spaces": false,
181
+ "eos_token": "<|endoftext|>",
182
+ "extra_special_tokens": {},
183
+ "max_length": null,
184
+ "model_max_length": 1000000000000000019884624838656,
185
+ "pad_token": "<|pad|>",
186
+ "tokenizer_class": "OLMoTokenizerFast",
187
+ "truncation": "right"
188
+ }
train.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc2b66af2b396792282fdee92b27f0be2c0269544f0a4e968412889eeb91730
3
+ size 14997