update model
Browse files- olmo-1b-5000/config.json +0 -28
- olmo-1b-5000/generation_config.json +0 -6
- olmo-1b-5000/model.safetensors +0 -3
- olmo-1b-5000/special_tokens_map.json +0 -16
- olmo-1b-5000/tokenizer.json +0 -0
- olmo-1b-5000/tokenizer_config.json +0 -238
- olmo-1b-50000/config.json +0 -28
- olmo-1b-50000/generation_config.json +0 -6
- olmo-1b-50000/model.safetensors +0 -3
- olmo-1b-50000/special_tokens_map.json +0 -16
- olmo-1b-50000/tokenizer.json +0 -0
- olmo-1b-50000/tokenizer_config.json +0 -238
- olmo-1b-720000/config.json +0 -28
- olmo-1b-720000/generation_config.json +0 -6
- olmo-1b-720000/model.safetensors +0 -3
- olmo-1b-720000/special_tokens_map.json +0 -16
- olmo-1b-720000/tokenizer.json +0 -0
- olmo-1b-720000/tokenizer_config.json +0 -238
- olmo-1b-740000 +1 -0
olmo-1b-5000/config.json
DELETED
@@ -1,28 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "allenai/OLMo-1B-hf",
|
3 |
-
"architectures": [
|
4 |
-
"OlmoForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_bias": false,
|
7 |
-
"attention_dropout": 0.0,
|
8 |
-
"clip_qkv": null,
|
9 |
-
"eos_token_id": 50279,
|
10 |
-
"hidden_act": "silu",
|
11 |
-
"hidden_size": 2048,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 8192,
|
14 |
-
"max_position_embeddings": 2048,
|
15 |
-
"model_type": "olmo",
|
16 |
-
"num_attention_heads": 16,
|
17 |
-
"num_hidden_layers": 16,
|
18 |
-
"num_key_value_heads": 16,
|
19 |
-
"pad_token_id": 1,
|
20 |
-
"pretraining_tp": 1,
|
21 |
-
"rope_scaling": null,
|
22 |
-
"rope_theta": 10000.0,
|
23 |
-
"tie_word_embeddings": true,
|
24 |
-
"torch_dtype": "float32",
|
25 |
-
"transformers_version": "4.43.3",
|
26 |
-
"use_cache": true,
|
27 |
-
"vocab_size": 50304
|
28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-5000/generation_config.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"eos_token_id": 0,
|
4 |
-
"pad_token_id": 1,
|
5 |
-
"transformers_version": "4.43.3"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-5000/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:92fd5032f069d9f140c12d0e7937fa99f886d3c8d19faec00c5cb1ffad1adee9
|
3 |
-
size 4707070632
|
|
|
|
|
|
|
|
olmo-1b-5000/special_tokens_map.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"eos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"pad_token": {
|
10 |
-
"content": "<|padding|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
}
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-5000/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
olmo-1b-5000/tokenizer_config.json
DELETED
@@ -1,238 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": false,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": false,
|
5 |
-
"added_tokens_decoder": {
|
6 |
-
"0": {
|
7 |
-
"content": "|||IP_ADDRESS|||",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": true,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": false
|
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": "|||EMAIL_ADDRESS|||",
|
208 |
-
"lstrip": false,
|
209 |
-
"normalized": true,
|
210 |
-
"rstrip": false,
|
211 |
-
"single_word": false,
|
212 |
-
"special": false
|
213 |
-
},
|
214 |
-
"50278": {
|
215 |
-
"content": "|||PHONE_NUMBER|||",
|
216 |
-
"lstrip": false,
|
217 |
-
"normalized": true,
|
218 |
-
"rstrip": false,
|
219 |
-
"single_word": false,
|
220 |
-
"special": false
|
221 |
-
},
|
222 |
-
"50279": {
|
223 |
-
"content": "<|endoftext|>",
|
224 |
-
"lstrip": false,
|
225 |
-
"normalized": false,
|
226 |
-
"rstrip": false,
|
227 |
-
"single_word": false,
|
228 |
-
"special": true
|
229 |
-
}
|
230 |
-
},
|
231 |
-
"bos_token": null,
|
232 |
-
"clean_up_tokenization_spaces": true,
|
233 |
-
"eos_token": "<|endoftext|>",
|
234 |
-
"model_max_length": 1000000000000000019884624838656,
|
235 |
-
"pad_token": "<|padding|>",
|
236 |
-
"tokenizer_class": "GPTNeoXTokenizer",
|
237 |
-
"unk_token": null
|
238 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-50000/config.json
DELETED
@@ -1,28 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "allenai/OLMo-1B-hf",
|
3 |
-
"architectures": [
|
4 |
-
"OlmoForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_bias": false,
|
7 |
-
"attention_dropout": 0.0,
|
8 |
-
"clip_qkv": null,
|
9 |
-
"eos_token_id": 50279,
|
10 |
-
"hidden_act": "silu",
|
11 |
-
"hidden_size": 2048,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 8192,
|
14 |
-
"max_position_embeddings": 2048,
|
15 |
-
"model_type": "olmo",
|
16 |
-
"num_attention_heads": 16,
|
17 |
-
"num_hidden_layers": 16,
|
18 |
-
"num_key_value_heads": 16,
|
19 |
-
"pad_token_id": 1,
|
20 |
-
"pretraining_tp": 1,
|
21 |
-
"rope_scaling": null,
|
22 |
-
"rope_theta": 10000.0,
|
23 |
-
"tie_word_embeddings": true,
|
24 |
-
"torch_dtype": "float32",
|
25 |
-
"transformers_version": "4.43.3",
|
26 |
-
"use_cache": true,
|
27 |
-
"vocab_size": 50304
|
28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-50000/generation_config.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"eos_token_id": 0,
|
4 |
-
"pad_token_id": 1,
|
5 |
-
"transformers_version": "4.43.3"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-50000/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:1e334f2ed4d5efb1b15fa0a12df6e3524880db688e6c8a2eb6a9196bd0305006
|
3 |
-
size 4707070632
|
|
|
|
|
|
|
|
olmo-1b-50000/special_tokens_map.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"eos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"pad_token": {
|
10 |
-
"content": "<|padding|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
}
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-50000/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
olmo-1b-50000/tokenizer_config.json
DELETED
@@ -1,238 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": false,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": false,
|
5 |
-
"added_tokens_decoder": {
|
6 |
-
"0": {
|
7 |
-
"content": "|||IP_ADDRESS|||",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": true,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": false
|
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": "|||EMAIL_ADDRESS|||",
|
208 |
-
"lstrip": false,
|
209 |
-
"normalized": true,
|
210 |
-
"rstrip": false,
|
211 |
-
"single_word": false,
|
212 |
-
"special": false
|
213 |
-
},
|
214 |
-
"50278": {
|
215 |
-
"content": "|||PHONE_NUMBER|||",
|
216 |
-
"lstrip": false,
|
217 |
-
"normalized": true,
|
218 |
-
"rstrip": false,
|
219 |
-
"single_word": false,
|
220 |
-
"special": false
|
221 |
-
},
|
222 |
-
"50279": {
|
223 |
-
"content": "<|endoftext|>",
|
224 |
-
"lstrip": false,
|
225 |
-
"normalized": false,
|
226 |
-
"rstrip": false,
|
227 |
-
"single_word": false,
|
228 |
-
"special": true
|
229 |
-
}
|
230 |
-
},
|
231 |
-
"bos_token": null,
|
232 |
-
"clean_up_tokenization_spaces": true,
|
233 |
-
"eos_token": "<|endoftext|>",
|
234 |
-
"model_max_length": 1000000000000000019884624838656,
|
235 |
-
"pad_token": "<|padding|>",
|
236 |
-
"tokenizer_class": "GPTNeoXTokenizer",
|
237 |
-
"unk_token": null
|
238 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-720000/config.json
DELETED
@@ -1,28 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "allenai/OLMo-1B-hf",
|
3 |
-
"architectures": [
|
4 |
-
"OlmoForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_bias": false,
|
7 |
-
"attention_dropout": 0.0,
|
8 |
-
"clip_qkv": null,
|
9 |
-
"eos_token_id": 50279,
|
10 |
-
"hidden_act": "silu",
|
11 |
-
"hidden_size": 2048,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 8192,
|
14 |
-
"max_position_embeddings": 2048,
|
15 |
-
"model_type": "olmo",
|
16 |
-
"num_attention_heads": 16,
|
17 |
-
"num_hidden_layers": 16,
|
18 |
-
"num_key_value_heads": 16,
|
19 |
-
"pad_token_id": 1,
|
20 |
-
"pretraining_tp": 1,
|
21 |
-
"rope_scaling": null,
|
22 |
-
"rope_theta": 10000.0,
|
23 |
-
"tie_word_embeddings": true,
|
24 |
-
"torch_dtype": "float32",
|
25 |
-
"transformers_version": "4.43.3",
|
26 |
-
"use_cache": true,
|
27 |
-
"vocab_size": 50304
|
28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-720000/generation_config.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"eos_token_id": 0,
|
4 |
-
"pad_token_id": 1,
|
5 |
-
"transformers_version": "4.43.3"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-720000/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f6206bd00ef9c8779903908704c3eeb9894506273a6ce56bdc3fbcbc5ba6197d
|
3 |
-
size 4707070632
|
|
|
|
|
|
|
|
olmo-1b-720000/special_tokens_map.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"eos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"pad_token": {
|
10 |
-
"content": "<|padding|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
}
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-720000/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
olmo-1b-720000/tokenizer_config.json
DELETED
@@ -1,238 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": false,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": false,
|
5 |
-
"added_tokens_decoder": {
|
6 |
-
"0": {
|
7 |
-
"content": "|||IP_ADDRESS|||",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": true,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": false
|
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": "|||EMAIL_ADDRESS|||",
|
208 |
-
"lstrip": false,
|
209 |
-
"normalized": true,
|
210 |
-
"rstrip": false,
|
211 |
-
"single_word": false,
|
212 |
-
"special": false
|
213 |
-
},
|
214 |
-
"50278": {
|
215 |
-
"content": "|||PHONE_NUMBER|||",
|
216 |
-
"lstrip": false,
|
217 |
-
"normalized": true,
|
218 |
-
"rstrip": false,
|
219 |
-
"single_word": false,
|
220 |
-
"special": false
|
221 |
-
},
|
222 |
-
"50279": {
|
223 |
-
"content": "<|endoftext|>",
|
224 |
-
"lstrip": false,
|
225 |
-
"normalized": false,
|
226 |
-
"rstrip": false,
|
227 |
-
"single_word": false,
|
228 |
-
"special": true
|
229 |
-
}
|
230 |
-
},
|
231 |
-
"bos_token": null,
|
232 |
-
"clean_up_tokenization_spaces": true,
|
233 |
-
"eos_token": "<|endoftext|>",
|
234 |
-
"model_max_length": 1000000000000000019884624838656,
|
235 |
-
"pad_token": "<|padding|>",
|
236 |
-
"tokenizer_class": "GPTNeoXTokenizer",
|
237 |
-
"unk_token": null
|
238 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
olmo-1b-740000
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
Subproject commit aee7752d9c08ee4775e9b0091426d8410e8f6a89
|