Hugging Face's logo

estrogen
/
olmoe-upscale

Text Generation
Transformers
Safetensors
olmoe
mergekit
mergekitty
Merge
conversational
Model card Files
xet
Community
Fizzarolli commited on
Commit
41df346
·
verified ·
1 Parent(s): 8496218

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. README.md +92 -0
  2. config.json +32 -0
  3. mergekitty_config.yml +61 -0
  4. model-00001-of-00005.safetensors +3 -0
  5. model-00002-of-00005.safetensors +3 -0
  6. model-00003-of-00005.safetensors +3 -0
  7. model-00004-of-00005.safetensors +3 -0
  8. model-00005-of-00005.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. special_tokens_map.json +23 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +248 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - allenai/OLMoE-1B-7B-0125-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - mergekitty
8
+ - merge
9
+
10
+ ---
11
+ # output2
12
+
13
+ This is a merge of pre-trained language models created using [mergekitty](https://github.com/allura-org/mergekitty).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the Passthrough merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [allenai/OLMoE-1B-7B-0125-Instruct](https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct)
24
+
25
+ ### Configuration
26
+
27
+ The following YAML configuration was used to produce this model:
28
+
29
+ ```yaml
30
+ dtype: bfloat16
31
+ merge_method: passthrough
32
+ slices:
33
+ - sources:
34
+ - layer_range: [0, 4]
35
+ model: allenai/OLMoE-1B-7B-0125-Instruct
36
+ - sources:
37
+ - layer_range: [4, 6]
38
+ model: allenai/OLMoE-1B-7B-0125-Instruct
39
+ - sources:
40
+ - layer_range: [4, 6]
41
+ model: allenai/OLMoE-1B-7B-0125-Instruct
42
+ parameters:
43
+ scale:
44
+ - filter: o_proj
45
+ value: 0.0
46
+ - filter: down_proj
47
+ value: 0.0
48
+ - value: 1.0
49
+ - sources:
50
+ - layer_range: [6, 8]
51
+ model: allenai/OLMoE-1B-7B-0125-Instruct
52
+ - sources:
53
+ - layer_range: [6, 8]
54
+ model: allenai/OLMoE-1B-7B-0125-Instruct
55
+ parameters:
56
+ scale:
57
+ - filter: o_proj
58
+ value: 0.0
59
+ - filter: down_proj
60
+ value: 0.0
61
+ - value: 1.0
62
+ - sources:
63
+ - layer_range: [8, 10]
64
+ model: allenai/OLMoE-1B-7B-0125-Instruct
65
+ - sources:
66
+ - layer_range: [8, 10]
67
+ model: allenai/OLMoE-1B-7B-0125-Instruct
68
+ parameters:
69
+ scale:
70
+ - filter: o_proj
71
+ value: 0.0
72
+ - filter: down_proj
73
+ value: 0.0
74
+ - value: 1.0
75
+ - sources:
76
+ - layer_range: [10, 12]
77
+ model: allenai/OLMoE-1B-7B-0125-Instruct
78
+ - sources:
79
+ - layer_range: [10, 12]
80
+ model: allenai/OLMoE-1B-7B-0125-Instruct
81
+ parameters:
82
+ scale:
83
+ - filter: o_proj
84
+ value: 0.0
85
+ - filter: down_proj
86
+ value: 0.0
87
+ - value: 1.0
88
+ - sources:
89
+ - layer_range: [12, 16]
90
+ model: allenai/OLMoE-1B-7B-0125-Instruct
91
+
92
+ ```
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "clip_qkv": null,
8
+ "eos_token_id": 50279,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1024,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "olmoe",
15
+ "norm_topk_prob": false,
16
+ "num_attention_heads": 16,
17
+ "num_experts": 64,
18
+ "num_experts_per_tok": 8,
19
+ "num_hidden_layers": 24,
20
+ "num_key_value_heads": 16,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "router_aux_loss_coef": 0.01,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.51.2",
30
+ "use_cache": false,
31
+ "vocab_size": 50281
32
+ }
mergekitty_config.yml ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - layer_range: [0, 4]
6
+ model: allenai/OLMoE-1B-7B-0125-Instruct
7
+ - sources:
8
+ - layer_range: [4, 6]
9
+ model: allenai/OLMoE-1B-7B-0125-Instruct
10
+ - sources:
11
+ - layer_range: [4, 6]
12
+ model: allenai/OLMoE-1B-7B-0125-Instruct
13
+ parameters:
14
+ scale:
15
+ - filter: o_proj
16
+ value: 0.0
17
+ - filter: down_proj
18
+ value: 0.0
19
+ - value: 1.0
20
+ - sources:
21
+ - layer_range: [6, 8]
22
+ model: allenai/OLMoE-1B-7B-0125-Instruct
23
+ - sources:
24
+ - layer_range: [6, 8]
25
+ model: allenai/OLMoE-1B-7B-0125-Instruct
26
+ parameters:
27
+ scale:
28
+ - filter: o_proj
29
+ value: 0.0
30
+ - filter: down_proj
31
+ value: 0.0
32
+ - value: 1.0
33
+ - sources:
34
+ - layer_range: [8, 10]
35
+ model: allenai/OLMoE-1B-7B-0125-Instruct
36
+ - sources:
37
+ - layer_range: [8, 10]
38
+ model: allenai/OLMoE-1B-7B-0125-Instruct
39
+ parameters:
40
+ scale:
41
+ - filter: o_proj
42
+ value: 0.0
43
+ - filter: down_proj
44
+ value: 0.0
45
+ - value: 1.0
46
+ - sources:
47
+ - layer_range: [10, 12]
48
+ model: allenai/OLMoE-1B-7B-0125-Instruct
49
+ - sources:
50
+ - layer_range: [10, 12]
51
+ model: allenai/OLMoE-1B-7B-0125-Instruct
52
+ parameters:
53
+ scale:
54
+ - filter: o_proj
55
+ value: 0.0
56
+ - filter: down_proj
57
+ value: 0.0
58
+ - value: 1.0
59
+ - sources:
60
+ - layer_range: [12, 16]
61
+ model: allenai/OLMoE-1B-7B-0125-Instruct
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d7908bde04db0b17e408893be00baa2f38b62fc0f90c81992cdf32ee4732bc
3
+ size 4997535280
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b9f933cce56deb1501c4fe853c6af7b1a21e375ad57c93a5188939a78cc7bb
3
+ size 4997510112
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4353c9aef2602b6f99db8a71f9c6fd60947d663046d737a163c16d3fd82f7e
3
+ size 4996960632
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cdd48ac97e79f346478510d6ff364a1fa28ca09347c4cd31355b8f3909104ee
3
+ size 4997235792
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055a49a9b7f196595d417b2398e59ab5309a4c2ec7bbe6664053d65f5d726123
3
+ size 562606112
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "|||IP_ADDRESS|||",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "|||IP_ADDRESS|||",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "|||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": "|||IP_ADDRESS|||",
224
+ "lstrip": false,
225
+ "normalized": true,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "50280": {
231
+ "content": "<pad>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ }
238
+ },
239
+ "bos_token": "|||IP_ADDRESS|||",
240
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
241
+ "clean_up_tokenization_spaces": false,
242
+ "eos_token": "|||IP_ADDRESS|||",
243
+ "extra_special_tokens": {},
244
+ "model_max_length": 1000000000000000019884624838656,
245
+ "pad_token": "<pad>",
246
+ "tokenizer_class": "GPTNeoXTokenizer",
247
+ "unk_token": null
248
+ }