Hugging Face's logo

shellwork
/
ChatParts-qwen2.5-14b

Question Answering
Safetensors
English
qwen2
biology
medical
Model card Files Community
shellwork commited on
Commit
cd54211
•
1 Parent(s): e9fb3d2

Upload 19 files

Browse files
Files changed (19) hide show
  1. .gitattributes +38 -35
  2. LICENSE +202 -0
  3. added_tokens.json +25 -0
  4. config.json +28 -0
  5. configuration.json +1 -0
  6. generation_config.json +14 -0
  7. model-00001-of-00008.safetensors +3 -0
  8. model-00002-of-00008.safetensors +3 -0
  9. model-00003-of-00008.safetensors +3 -0
  10. model-00004-of-00008.safetensors +3 -0
  11. model-00005-of-00008.safetensors +3 -0
  12. model-00006-of-00008.safetensors +3 -0
  13. model-00007-of-00008.safetensors +3 -0
  14. model-00008-of-00008.safetensors +3 -0
  15. model.safetensors.index.json +586 -0
  16. special_tokens_map.json +31 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +216 -0
  19. vocab.json +0 -0
.gitattributes CHANGED
@@ -1,35 +1,38 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.model filter=lfs diff=lfs merge=lfs -text
12
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
13
+ *.onnx filter=lfs diff=lfs merge=lfs -text
14
+ *.ot filter=lfs diff=lfs merge=lfs -text
15
+ *.parquet filter=lfs diff=lfs merge=lfs -text
16
+ *.pb filter=lfs diff=lfs merge=lfs -text
17
+ *.pt filter=lfs diff=lfs merge=lfs -text
18
+ *.pth filter=lfs diff=lfs merge=lfs -text
19
+ *.rar filter=lfs diff=lfs merge=lfs -text
20
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
21
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
22
+ *.tflite filter=lfs diff=lfs merge=lfs -text
23
+ *.tgz filter=lfs diff=lfs merge=lfs -text
24
+ *.xz filter=lfs diff=lfs merge=lfs -text
25
+ *.zip filter=lfs diff=lfs merge=lfs -text
26
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
27
+ *.tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.db* filter=lfs diff=lfs merge=lfs -text
29
+ *.ark* filter=lfs diff=lfs merge=lfs -text
30
+ **/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
31
+ **/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
32
+ **/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
33
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
34
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
35
+ *.gguf* filter=lfs diff=lfs merge=lfs -text
36
+ *.ggml filter=lfs diff=lfs merge=lfs -text
37
+ *.llamafile* filter=lfs diff=lfs merge=lfs -text
38
+ *.pt2 filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright 2024 Alibaba Cloud
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|eot_id|>": 151665,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/autodl-tmp/trained_model/chatpartss_pre_comb",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.43.3",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"framework":"Pytorch","task":"question-answering"}
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.43.3"
14
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2220fe4b41fc08d4683a7f19525288e25fb6a2af82157595b0fe4463e074e2
3
+ size 3885134104
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a739da9a064ac6f418c33934e49dc613e247fa51c78590120b390d4a6aedd0d4
3
+ size 3995327992
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88e9c3575989ca045f5e0a4c086f6c8289ce891707591485ac8aaf95730ca75
3
+ size 3995328064
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf0ec854e716191feae62a611eef917f82fe787f7962cbe563b0e206e408348
3
+ size 3995348776
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ceceb63fa97c80224802422c7a6e430048cbaac89cc09a6c801ae1a48b9bdac
3
+ size 3979614448
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279db31adc60e1c3a00eb0168913df04be8f87911f43c9a291ab776c38deafe7
3
+ size 3995328064
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71474be52088d4a7519d808e6771a409717fe3b16bf1f5fb1872c0ecf8509509
3
+ size 3995328064
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1273734d47e1a590d04b9941b1fec2b4e3599913bb46b15f9c50836ef473ff52
3
+ size 1698724408
model.safetensors.index.json ADDED
@@ -0,0 +1,586 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29540067328
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00008-of-00008.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00008.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00008.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00008.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00007-of-00008.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00008-of-00008.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
524
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
525
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
526
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
527
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
528
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
529
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
530
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
531
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
532
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
533
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
534
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
535
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
536
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
537
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
538
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
539
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
540
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
541
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
542
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
543
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
544
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
545
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
546
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
547
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
548
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
549
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
550
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
551
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
552
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
553
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
554
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
555
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
556
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
557
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
558
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
559
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
560
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
561
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
562
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
563
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
564
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
565
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
566
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
567
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
568
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
569
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
570
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
571
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
572
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
573
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
574
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
575
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
576
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
577
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
578
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
579
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
580
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
581
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
582
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
583
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
584
+ "model.norm.weight": "model-00008-of-00008.safetensors"
585
+ }
586
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|eot_id|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
207
+ "clean_up_tokenization_spaces": false,
208
+ "eos_token": "<|im_end|>",
209
+ "errors": "replace",
210
+ "model_max_length": 131072,
211
+ "pad_token": "<|endoftext|>",
212
+ "padding_side": "left",
213
+ "split_special_tokens": false,
214
+ "tokenizer_class": "Qwen2Tokenizer",
215
+ "unk_token": null
216
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff