Hugging Face's logo

allenai
/
OLMo-2-1124-7B

Safetensors
English
olmo2
Model card Files
xet
Community
9
amanrangapur commited on
Commit
8fc681b
·
verified ·
1 Parent(s): cb5ef38

upload checkpoint

Browse files
Files changed (12) hide show
  1. config.json +3 -3
  2. merges.txt +0 -0
  3. model-00001-of-00006.safetensors +1 -1
  4. model-00002-of-00006.safetensors +1 -1
  5. model-00003-of-00006.safetensors +1 -1
  6. model-00004-of-00006.safetensors +1 -1
  7. model-00005-of-00006.safetensors +1 -1
  8. model-00006-of-00006.safetensors +1 -1
  9. special_tokens_map.json +6 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +189 -0
  12. vocab.json +0 -0
config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "architectures": [
3
- "Olmo2ForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
@@ -10,7 +10,7 @@
10
  "initializer_range": 0.02,
11
  "intermediate_size": 11008,
12
  "max_position_embeddings": 4096,
13
- "model_type": "olmo2",
14
  "num_attention_heads": 32,
15
  "num_hidden_layers": 32,
16
  "num_key_value_heads": 32,
@@ -23,4 +23,4 @@
23
  "transformers_version": "4.47.0.dev0",
24
  "use_cache": true,
25
  "vocab_size": 100352
26
- }
 
1
  {
2
  "architectures": [
3
+ "Olmo1124ForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
 
10
  "initializer_range": 0.02,
11
  "intermediate_size": 11008,
12
  "max_position_embeddings": 4096,
13
+ "model_type": "olmo_1124",
14
  "num_attention_heads": 32,
15
  "num_hidden_layers": 32,
16
  "num_key_value_heads": 32,
 
23
  "transformers_version": "4.47.0.dev0",
24
  "use_cache": true,
25
  "vocab_size": 100352
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9acbd5400251483e072c8371d3a17686f383041ada299f42de5894a1c69a115
3
  size 4949546184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880c0d9bd7311ca020584a7304504918dfcf17bfa35b464b1ab8dc01a06138d3
3
  size 4949546184
model-00002-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13e6a554cbe34802e3a5b1da8034c2c63e230d90418fb3ed37d2a9065972634b
3
  size 4991622816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0b6a357d03676c4986588aaf4dc96afc3f44a0498514961d2b2cfa1940655e
3
  size 4991622816
model-00003-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcd6a1c1456bbada7c54ba4f9721686a9abfb87a6191086d08d6bac0020a449f
3
  size 4924546896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1038a7d346a681a8fb6949e054c2246f3f3c80e826855c1cec6af1155cc607d
3
  size 4924546896
model-00004-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8fee0b2ffba48ef79c156581e40941f0b965894814122fc9f0b8dc0781f7b63
3
  size 4857404928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c0a21146ace02d36928787ae7f34be868f7c81b894dea98ec7b0e5a3ea01b2
3
  size 4857404928
model-00005-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fff56255111de019dab55e3c266e852bd36d5dec1cec827a379fd9fa0e93ae35
3
  size 4857404928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f82a3014ccfc0f67208f63785ae4bc71f09aba86db48bf6139d18178abbfed
3
  size 4857404928
model-00006-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f39f6b467af99ffbf0f51022980f2ebc1dc26ac11e2ae9313922f92fa456e4ba
3
  size 4613984792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dda0bdc36c113e54909a798f8847f76f052b17a082ceaf1fa8b0fd30b0b3041
3
  size 4613984792
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|pad|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|extra_id_0|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": false
11
+ },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "|||PHONE_NUMBER|||",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "100262": {
53
+ "content": "|||EMAIL_ADDRESS|||",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "100263": {
61
+ "content": "|||IP_ADDRESS|||",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "100264": {
69
+ "content": "<|im_start|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|im_end|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|extra_id_1|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "100267": {
93
+ "content": "<|extra_id_2|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "100268": {
101
+ "content": "<|extra_id_3|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "100269": {
109
+ "content": "<|extra_id_4|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "100270": {
117
+ "content": "<|extra_id_5|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "100271": {
125
+ "content": "<|extra_id_6|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "100272": {
133
+ "content": "<|extra_id_7|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "100273": {
141
+ "content": "<|extra_id_8|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "100274": {
149
+ "content": "<|extra_id_9|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "100275": {
157
+ "content": "<|extra_id_10|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100277": {
173
+ "content": "<|pad|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ }
180
+ },
181
+ "bos_token": "<|endoftext|>",
182
+ "clean_up_tokenization_spaces": false,
183
+ "eos_token": "<|endoftext|>",
184
+ "extra_special_tokens": {},
185
+ "model_max_length": 1000000000000000019884624838656,
186
+ "pad_token": "<|pad|>",
187
+ "tokenizer_class": "GPT2Tokenizer",
188
+ "unk_token": "<|endoftext|>"
189
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff