guteentag
commited on
Commit
•
6bc9a60
1
Parent(s):
35807e4
finetuned alpaca-7b
Browse files- LICENSE +201 -0
- config.json +24 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00039.bin +3 -0
- pytorch_model-00002-of-00039.bin +3 -0
- pytorch_model-00003-of-00039.bin +3 -0
- pytorch_model-00004-of-00039.bin +3 -0
- pytorch_model-00005-of-00039.bin +3 -0
- pytorch_model-00006-of-00039.bin +3 -0
- pytorch_model-00007-of-00039.bin +3 -0
- pytorch_model-00008-of-00039.bin +3 -0
- pytorch_model-00009-of-00039.bin +3 -0
- pytorch_model-00010-of-00039.bin +3 -0
- pytorch_model-00011-of-00039.bin +3 -0
- pytorch_model-00012-of-00039.bin +3 -0
- pytorch_model-00013-of-00039.bin +3 -0
- pytorch_model-00014-of-00039.bin +3 -0
- pytorch_model-00015-of-00039.bin +3 -0
- pytorch_model-00016-of-00039.bin +3 -0
- pytorch_model-00017-of-00039.bin +3 -0
- pytorch_model-00018-of-00039.bin +3 -0
- pytorch_model-00019-of-00039.bin +3 -0
- pytorch_model-00020-of-00039.bin +3 -0
- pytorch_model-00021-of-00039.bin +3 -0
- pytorch_model-00022-of-00039.bin +3 -0
- pytorch_model-00023-of-00039.bin +3 -0
- pytorch_model-00024-of-00039.bin +3 -0
- pytorch_model-00025-of-00039.bin +3 -0
- pytorch_model-00026-of-00039.bin +3 -0
- pytorch_model-00027-of-00039.bin +3 -0
- pytorch_model-00028-of-00039.bin +3 -0
- pytorch_model-00029-of-00039.bin +3 -0
- pytorch_model-00030-of-00039.bin +3 -0
- pytorch_model-00031-of-00039.bin +3 -0
- pytorch_model-00032-of-00039.bin +3 -0
- pytorch_model-00033-of-00039.bin +3 -0
- pytorch_model-00034-of-00039.bin +3 -0
- pytorch_model-00035-of-00039.bin +3 -0
- pytorch_model-00036-of-00039.bin +3 -0
- pytorch_model-00037-of-00039.bin +3 -0
- pytorch_model-00038-of-00039.bin +3 -0
- pytorch_model-00039-of-00039.bin +3 -0
- pytorch_model.bin.index.json +330 -0
- special_tokens_map.json +23 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
LICENSE
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Apache License
|
2 |
+
Version 2.0, January 2004
|
3 |
+
http://www.apache.org/licenses/
|
4 |
+
|
5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6 |
+
|
7 |
+
1. Definitions.
|
8 |
+
|
9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
11 |
+
|
12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13 |
+
the copyright owner that is granting the License.
|
14 |
+
|
15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
16 |
+
other entities that control, are controlled by, or are under common
|
17 |
+
control with that entity. For the purposes of this definition,
|
18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
19 |
+
direction or management of such entity, whether by contract or
|
20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22 |
+
|
23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24 |
+
exercising permissions granted by this License.
|
25 |
+
|
26 |
+
"Source" form shall mean the preferred form for making modifications,
|
27 |
+
including but not limited to software source code, documentation
|
28 |
+
source, and configuration files.
|
29 |
+
|
30 |
+
"Object" form shall mean any form resulting from mechanical
|
31 |
+
transformation or translation of a Source form, including but
|
32 |
+
not limited to compiled object code, generated documentation,
|
33 |
+
and conversions to other media types.
|
34 |
+
|
35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
36 |
+
Object form, made available under the License, as indicated by a
|
37 |
+
copyright notice that is included in or attached to the work
|
38 |
+
(an example is provided in the Appendix below).
|
39 |
+
|
40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41 |
+
form, that is based on (or derived from) the Work and for which the
|
42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
44 |
+
of this License, Derivative Works shall not include works that remain
|
45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46 |
+
the Work and Derivative Works thereof.
|
47 |
+
|
48 |
+
"Contribution" shall mean any work of authorship, including
|
49 |
+
the original version of the Work and any modifications or additions
|
50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
54 |
+
means any form of electronic, verbal, or written communication sent
|
55 |
+
to the Licensor or its representatives, including but not limited to
|
56 |
+
communication on electronic mailing lists, source code control systems,
|
57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
59 |
+
excluding communication that is conspicuously marked or otherwise
|
60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
61 |
+
|
62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
64 |
+
subsequently incorporated within the Work.
|
65 |
+
|
66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
71 |
+
Work and such Derivative Works in Source or Object form.
|
72 |
+
|
73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76 |
+
(except as stated in this section) patent license to make, have made,
|
77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78 |
+
where such license applies only to those patent claims licensable
|
79 |
+
by such Contributor that are necessarily infringed by their
|
80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
82 |
+
institute patent litigation against any entity (including a
|
83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84 |
+
or a Contribution incorporated within the Work constitutes direct
|
85 |
+
or contributory patent infringement, then any patent licenses
|
86 |
+
granted to You under this License for that Work shall terminate
|
87 |
+
as of the date such litigation is filed.
|
88 |
+
|
89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
90 |
+
Work or Derivative Works thereof in any medium, with or without
|
91 |
+
modifications, and in Source or Object form, provided that You
|
92 |
+
meet the following conditions:
|
93 |
+
|
94 |
+
(a) You must give any other recipients of the Work or
|
95 |
+
Derivative Works a copy of this License; and
|
96 |
+
|
97 |
+
(b) You must cause any modified files to carry prominent notices
|
98 |
+
stating that You changed the files; and
|
99 |
+
|
100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
101 |
+
that You distribute, all copyright, patent, trademark, and
|
102 |
+
attribution notices from the Source form of the Work,
|
103 |
+
excluding those notices that do not pertain to any part of
|
104 |
+
the Derivative Works; and
|
105 |
+
|
106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107 |
+
distribution, then any Derivative Works that You distribute must
|
108 |
+
include a readable copy of the attribution notices contained
|
109 |
+
within such NOTICE file, excluding those notices that do not
|
110 |
+
pertain to any part of the Derivative Works, in at least one
|
111 |
+
of the following places: within a NOTICE text file distributed
|
112 |
+
as part of the Derivative Works; within the Source form or
|
113 |
+
documentation, if provided along with the Derivative Works; or,
|
114 |
+
within a display generated by the Derivative Works, if and
|
115 |
+
wherever such third-party notices normally appear. The contents
|
116 |
+
of the NOTICE file are for informational purposes only and
|
117 |
+
do not modify the License. You may add Your own attribution
|
118 |
+
notices within Derivative Works that You distribute, alongside
|
119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
120 |
+
that such additional attribution notices cannot be construed
|
121 |
+
as modifying the License.
|
122 |
+
|
123 |
+
You may add Your own copyright statement to Your modifications and
|
124 |
+
may provide additional or different license terms and conditions
|
125 |
+
for use, reproduction, or distribution of Your modifications, or
|
126 |
+
for any such Derivative Works as a whole, provided Your use,
|
127 |
+
reproduction, and distribution of the Work otherwise complies with
|
128 |
+
the conditions stated in this License.
|
129 |
+
|
130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
132 |
+
by You to the Licensor shall be under the terms and conditions of
|
133 |
+
this License, without any additional terms or conditions.
|
134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135 |
+
the terms of any separate license agreement you may have executed
|
136 |
+
with Licensor regarding such Contributions.
|
137 |
+
|
138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
140 |
+
except as required for reasonable and customary use in describing the
|
141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
142 |
+
|
143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144 |
+
agreed to in writing, Licensor provides the Work (and each
|
145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147 |
+
implied, including, without limitation, any warranties or conditions
|
148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150 |
+
appropriateness of using or redistributing the Work and assume any
|
151 |
+
risks associated with Your exercise of permissions under this License.
|
152 |
+
|
153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
154 |
+
whether in tort (including negligence), contract, or otherwise,
|
155 |
+
unless required by applicable law (such as deliberate and grossly
|
156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157 |
+
liable to You for damages, including any direct, indirect, special,
|
158 |
+
incidental, or consequential damages of any character arising as a
|
159 |
+
result of this License or out of the use or inability to use the
|
160 |
+
Work (including but not limited to damages for loss of goodwill,
|
161 |
+
work stoppage, computer failure or malfunction, or any and all
|
162 |
+
other commercial damages or losses), even if such Contributor
|
163 |
+
has been advised of the possibility of such damages.
|
164 |
+
|
165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168 |
+
or other liability obligations and/or rights consistent with this
|
169 |
+
License. However, in accepting such obligations, You may act only
|
170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171 |
+
of any other Contributor, and only if You agree to indemnify,
|
172 |
+
defend, and hold each Contributor harmless for any liability
|
173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
174 |
+
of your accepting any such warranty or additional liability.
|
175 |
+
|
176 |
+
END OF TERMS AND CONDITIONS
|
177 |
+
|
178 |
+
APPENDIX: How to apply the Apache License to your work.
|
179 |
+
|
180 |
+
To apply the Apache License to your work, attach the following
|
181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
182 |
+
replaced with your own identifying information. (Don't include
|
183 |
+
the brackets!) The text should be enclosed in the appropriate
|
184 |
+
comment syntax for the file format. We also recommend that a
|
185 |
+
file or class name and description of purpose be included on the
|
186 |
+
same "printed page" as the copyright notice for easier
|
187 |
+
identification within third-party archives.
|
188 |
+
|
189 |
+
Copyright 2023 Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li
|
190 |
+
|
191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192 |
+
you may not use this file except in compliance with the License.
|
193 |
+
You may obtain a copy of the License at
|
194 |
+
|
195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
196 |
+
|
197 |
+
Unless required by applicable law or agreed to in writing, software
|
198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200 |
+
See the License for the specific language governing permissions and
|
201 |
+
limitations under the License.
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "decapoda-research/llama-7b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 1,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"max_sequence_length": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"pad_token_id": -1,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "float16",
|
21 |
+
"transformers_version": "4.28.0.dev0",
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 32000
|
24 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.0.dev0"
|
7 |
+
}
|
pytorch_model-00001-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46bc2e0da9e612f7b04a77c250839b0396c6a5b1cce4806befdcbdc0ed4ed803
|
3 |
+
size 396364479
|
pytorch_model-00002-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2126c027c98725fe8c302352feb409bd4fce6f4d71c501fa6bbdca7223f418ee
|
3 |
+
size 371215393
|
pytorch_model-00003-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da5116ca7ec4a6bba21f12ad1da0590fd3f34954c53b684d07dbf52c8642834e
|
3 |
+
size 371215986
|
pytorch_model-00004-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a3447281f125e1eead57cf6983b721e8d9d9669cad04304b4687045a88bfc12
|
3 |
+
size 371215986
|
pytorch_model-00005-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b59ffaedb8266d798d07f85a9621446f11658f81bb61dd403498d4daf15fe1a6
|
3 |
+
size 371215986
|
pytorch_model-00006-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7a7afc23ab49d1f8b6e097133d5fa6d9b53d8e8001f48d7940a71687c31779a
|
3 |
+
size 314575888
|
pytorch_model-00007-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce7d2b81b0c3af0cf58a90b05a056f9ee9f0b41e2a6bfea0ed10fa90290f7896
|
3 |
+
size 314592882
|
pytorch_model-00008-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b897583757e409adef9bfcaf1b2c24d70a666ce5da509d4093efcaca8575886a
|
3 |
+
size 314592882
|
pytorch_model-00009-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4562da93f501d3c75bc2e04f94d112689c1979e3a8383feac0001d437dc02ce1
|
3 |
+
size 371215393
|
pytorch_model-00010-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd9c7702447513610f4430c213401e8b6a9069fcf08c4d6e6ae9f5e1b6b53a0
|
3 |
+
size 371215986
|
pytorch_model-00011-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3f4c575284f1665fcd2a614cf924242c6c6c3f5135ff6aa13b9cc15b660cbc
|
3 |
+
size 371215986
|
pytorch_model-00012-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:643a658d10dbdea9398b8b8b1e7235eb6cb14e98c0b49c7c14a10faa180b822c
|
3 |
+
size 371215986
|
pytorch_model-00013-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f560407d80ec81afc23a4803c520fd4f0b2d67b3fc6da6c5eef690d2fc5007d2
|
3 |
+
size 314575888
|
pytorch_model-00014-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29db5c2818a134b142b8b9a7e49f331cb56da4edf2aa946c7935b0e34291a00d
|
3 |
+
size 314592882
|
pytorch_model-00015-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45a41d58937de4e245379e74a0c84a7e7b7e2b5fbb53ced76de39eb9b1143afb
|
3 |
+
size 314592882
|
pytorch_model-00016-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33b9a4122a3c9aa31c1a50afec91ac540d7b3c6169765ed1a89e352b30257c1e
|
3 |
+
size 371215393
|
pytorch_model-00017-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54f00f6e2bcc7d374f0dbd5420b8cfa8e1dd17efb76d1048fc3b424b89a1bfe5
|
3 |
+
size 371215986
|
pytorch_model-00018-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03499f8c95488ce10b162c0ce0b05fc50aee48d402a2d485ae071f3aa50d61f8
|
3 |
+
size 371215986
|
pytorch_model-00019-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9627578ad09ca9bd195a54174f154c6099415046db317d61a530df9e5ca64e5
|
3 |
+
size 371215986
|
pytorch_model-00020-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cb51ece4065062d6bba0ef17d34b274dad78f845d196de60a09bc95f48e4b69
|
3 |
+
size 314575888
|
pytorch_model-00021-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94410ce32509dac683ae8e70ad037d2b9a6507137b1575d4e0e13b992208d266
|
3 |
+
size 314592882
|
pytorch_model-00022-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1075b0d699cfc0fb6aa68dc2bb6eab9f6e0cec47889c9ec385132c26b240d9a0
|
3 |
+
size 314592882
|
pytorch_model-00023-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf2659f815207821f725ba6b426d41e3b5b4c31e681ba20e02f9862f23e8b3f
|
3 |
+
size 371215393
|
pytorch_model-00024-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dbea9a4c50518739b1a82530e2e11f64ff0a5344acfe4df3287cfd987f68195
|
3 |
+
size 371215986
|
pytorch_model-00025-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9761eb24a942441038c55e9a37407c6aa5744159b10463c542e3b52b689694e5
|
3 |
+
size 371215986
|
pytorch_model-00026-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1856bc0c3186fe49172fff87e1f5c2c8e5e6c713e4e14e3a12e02bf34bc4694a
|
3 |
+
size 371215986
|
pytorch_model-00027-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ca9c61ea107ed4810fda2a481563a9f31d85ebbd784b5b8a1ac69140c73d1a8
|
3 |
+
size 314575888
|
pytorch_model-00028-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bdd35381b82dc7a9f6eaad83b76059a4970a8c3782c8d5474da95fdecd22861
|
3 |
+
size 314592882
|
pytorch_model-00029-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f4e4a2091594182f35a701b14dee15f3d119eecc2fe730d3e0736a110d2dc59
|
3 |
+
size 314592882
|
pytorch_model-00030-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e8601a6bda2dfc48ea9268920aed5ff39fdf55fe1397bd4459da48592bf1a09
|
3 |
+
size 371215393
|
pytorch_model-00031-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b71362e8d58274ad755b81d532c12ce4103a473320232d9928d72a719eb96b3
|
3 |
+
size 371215986
|
pytorch_model-00032-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09a30b9ac5a018082456667378a751dd5870fadc09cf3d024e85f020f96b3ec2
|
3 |
+
size 371215986
|
pytorch_model-00033-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84a463aeeca232048509e8030d52e2b8d17a128e8087dad054d25823bba18cd9
|
3 |
+
size 371215986
|
pytorch_model-00034-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfe5beda4dcef173e705c4fff7bb4dd5bef64ccc4f48de7d3c0c63d96a9d5b43
|
3 |
+
size 314575888
|
pytorch_model-00035-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b013710e6c8157f2735789caec33e55b0946cf09f886fd85381544c18f11da35
|
3 |
+
size 314592882
|
pytorch_model-00036-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e18deb38a02d274b4c43b9eea2af0945ee86f1dc6020d8e197be7e2e2ee60181
|
3 |
+
size 314592882
|
pytorch_model-00037-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ebde181e8ac45b6519e3a8bfbf35338f7164d16e8ea443a92004f9649155d56
|
3 |
+
size 371215393
|
pytorch_model-00038-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6762c675eb30868665ce8ada7a2bbbd117e02f44d47ba3c8dcf91f5623e5ce67
|
3 |
+
size 304114977
|
pytorch_model-00039-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3350fb71c2bc1e88d77d9685716fd2759e879137814a4120d98265a43f405919
|
3 |
+
size 262144938
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476839424
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00039-of-00039.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin",
|
16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin",
|
268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin",
|
270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin",
|
271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin",
|
272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin",
|
274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin",
|
275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin",
|
276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin",
|
277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin",
|
278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin",
|
280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin",
|
281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin",
|
282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin",
|
284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin",
|
286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin",
|
288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin",
|
290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin",
|
291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin",
|
292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin",
|
294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin",
|
295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin",
|
296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin",
|
297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin",
|
298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin",
|
300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin",
|
301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin",
|
302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin",
|
304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin",
|
305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin",
|
306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin",
|
307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin",
|
308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin",
|
310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin",
|
311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin",
|
312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin",
|
314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin",
|
315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin",
|
316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin",
|
317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin",
|
318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin",
|
320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin",
|
321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin",
|
322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin",
|
326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin",
|
327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin",
|
328 |
+
"model.norm.weight": "pytorch_model-00038-of-00039.bin"
|
329 |
+
}
|
330 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"pad_token": null,
|
23 |
+
"sp_model_kwargs": {},
|
24 |
+
"special_tokens_map_file": "/home/sunyishen/.cache/huggingface/hub/models--decapoda-research--llama-7b-hf/snapshots/5f98eefcc80e437ef68d457ad7bf167c2c6a1348/special_tokens_map.json",
|
25 |
+
"tokenizer_class": "LlamaTokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|