merge version v20240318
#2
by
itsliupeng
- opened
- CHANGELOG.md +0 -12
- LICENSE +0 -201
- README.md +97 -255
- images/initail.png +0 -0
- images/v20240318.png +0 -0
- images/v20240321.png +0 -0
- md5 +4 -4
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- tokenizer.json +9 -2068
CHANGELOG.md
DELETED
@@ -1,12 +0,0 @@
|
|
1 |
-
|
2 |
-
## version: v20240321
|
3 |
-
- train 17B tokens with 256k context window
|
4 |
-
- recall of "Needle in A HayStack": 99.0% ![](./images/v20240321.png)
|
5 |
-
|
6 |
-
## version: v20240318
|
7 |
-
- train 12B tokens with 256k context window
|
8 |
-
- recall of "Needle in A HayStack": 97.5% ![](./images/v20240318.png)
|
9 |
-
|
10 |
-
## version: initial
|
11 |
-
- train 6B tokens with 256k context window
|
12 |
-
- recall of "Needle in A HayStack": 87.1% ![](./images/initail.png)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
LICENSE
DELETED
@@ -1,201 +0,0 @@
|
|
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 2024 01.AI
|
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.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
README.md
CHANGED
@@ -1,5 +1,7 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
3 |
widget:
|
4 |
- example_title: "Yi-34B-Chat"
|
5 |
text: "hi"
|
@@ -29,6 +31,18 @@ pipeline_tag: text-generation
|
|
29 |
</a>
|
30 |
</div>
|
31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
<div style="display: inline-block;">
|
33 |
<a href="mailto:oss@01.ai">
|
34 |
<img src="https://img.shields.io/badge/✉️-yi@01.ai-FFE01B">
|
@@ -46,20 +60,10 @@ pipeline_tag: text-generation
|
|
46 |
</p>
|
47 |
|
48 |
<p align="center">
|
49 |
-
|
50 |
</p>
|
51 |
|
52 |
-
<p align="center">
|
53 |
-
👋 Join us on <a href="https://discord.gg/hYUwWddeAu" target="_blank"> 👾 Discord </a> or <a href="有官方的微信群嘛 · Issue #43 · 01-ai/Yi" target="_blank"> 💬 WeChat </a>
|
54 |
-
</p>
|
55 |
|
56 |
-
<p align="center">
|
57 |
-
📝 Check out <a href="https://arxiv.org/abs/2403.04652"> Yi Tech Report </a>
|
58 |
-
</p>
|
59 |
-
|
60 |
-
<p align="center">
|
61 |
-
📚 Grow at <a href="#learning-hub"> Yi Learning Hub </a>
|
62 |
-
</p>
|
63 |
<!-- DO NOT REMOVE ME -->
|
64 |
|
65 |
<hr>
|
@@ -72,7 +76,7 @@ pipeline_tag: text-generation
|
|
72 |
- [Models](#models)
|
73 |
- [Chat models](#chat-models)
|
74 |
- [Base models](#base-models)
|
75 |
-
- [
|
76 |
- [News](#news)
|
77 |
- [How to use Yi?](#how-to-use-yi)
|
78 |
- [Quick start](#quick-start)
|
@@ -85,7 +89,6 @@ pipeline_tag: text-generation
|
|
85 |
- [Fine-tuning](#fine-tuning)
|
86 |
- [Quantization](#quantization)
|
87 |
- [Deployment](#deployment)
|
88 |
-
- [FAQ](#faq)
|
89 |
- [Learning hub](#learning-hub)
|
90 |
- [Why Yi?](#why-yi)
|
91 |
- [Ecosystem](#ecosystem)
|
@@ -119,14 +122,13 @@ pipeline_tag: text-generation
|
|
119 |
- 🙌 Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example,
|
120 |
|
121 |
- Yi-34B-Chat model **landed in second place (following GPT-4 Turbo)**, outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024).
|
122 |
-
|
123 |
- Yi-34B model **ranked first among all existing open-source models** (such as Falcon-180B, Llama-70B, Claude) in **both English and Chinese** on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023).
|
124 |
|
125 |
- 🙏 (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem.
|
126 |
|
127 |
<details style="display: inline;"><summary> If you're interested in Yi's adoption of Llama architecture and license usage policy, see <span style="color: green;">Yi's relation with Llama.</span> ⬇️</summary> <ul> <br>
|
128 |
|
129 |
-
|
130 |
> 💡 TL;DR
|
131 |
>
|
132 |
> The Yi series models adopt the same model architecture as Llama but are **NOT** derivatives of Llama.
|
@@ -151,19 +153,7 @@ pipeline_tag: text-generation
|
|
151 |
|
152 |
## News
|
153 |
|
154 |
-
<details>
|
155 |
-
<summary>🔥 <b>2024-07-29</b>: The <a href="https://github.com/Haijian06/Yi/tree/main/Cookbook">Yi Cookbook 1.0 </a> is released, featuring tutorials and examples in both Chinese and English.</summary>
|
156 |
-
</details>
|
157 |
-
|
158 |
-
<details>
|
159 |
-
<summary>🎯 <b>2024-05-13</b>: The <a href="https://github.com/01-ai/Yi-1.5">Yi-1.5 series models </a> are open-sourced, further improving coding, math, reasoning, and instruction-following abilities.</summary>
|
160 |
-
</details>
|
161 |
-
|
162 |
-
<details>
|
163 |
-
<summary>🎯 <b>2024-03-16</b>: The <code>Yi-9B-200K</code> is open-sourced and available to the public.</summary>
|
164 |
-
</details>
|
165 |
-
|
166 |
-
<details>
|
167 |
<summary>🎯 <b>2024-03-08</b>: <a href="https://arxiv.org/abs/2403.04652">Yi Tech Report</a> is published! </summary>
|
168 |
</details>
|
169 |
|
@@ -242,27 +232,28 @@ If you want to deploy Yi models, make sure you meet the [software and hardware r
|
|
242 |
|
243 |
### Chat models
|
244 |
|
245 |
-
| Model | Download
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
|
|
253 |
|
254 |
<sub><sup> - 4-bit series models are quantized by AWQ. <br> - 8-bit series models are quantized by GPTQ <br> - All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). </sup></sub>
|
255 |
|
256 |
### Base models
|
257 |
|
258 |
-
| Model | Download |
|
259 |
|---|---|
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
|
267 |
<sub><sup> - 200k is roughly equivalent to 400,000 Chinese characters. <br> - If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run `git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf` to download the weight. </sup></sub>
|
268 |
|
@@ -270,35 +261,11 @@ If you want to deploy Yi models, make sure you meet the [software and hardware r
|
|
270 |
|
271 |
- For chat and base models
|
272 |
|
273 |
-
|
274 |
-
|
275 |
-
|
276 |
-
|
277 |
-
|
278 |
-
<th>Default context window</th>
|
279 |
-
<th>Pretrained tokens</th>
|
280 |
-
<th>Training Data Date</th>
|
281 |
-
</tr>
|
282 |
-
</thead>
|
283 |
-
<tbody><tr>
|
284 |
-
<td>6B series models</td>
|
285 |
-
<td>They are suitable for personal and academic use.</td>
|
286 |
-
<td rowspan="3">4K</td>
|
287 |
-
<td>3T</td>
|
288 |
-
<td rowspan="3">Up to June 2023</td>
|
289 |
-
</tr>
|
290 |
-
<tr>
|
291 |
-
<td>9B series models</td>
|
292 |
-
<td>It is the best at coding and math in the Yi series models.</td>
|
293 |
-
<td>Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens.</td>
|
294 |
-
</tr>
|
295 |
-
<tr>
|
296 |
-
<td>34B series models</td>
|
297 |
-
<td>They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability.</td>
|
298 |
-
<td>3T</td>
|
299 |
-
</tr>
|
300 |
-
</tbody></table>
|
301 |
-
|
302 |
|
303 |
- For chat models
|
304 |
|
@@ -311,8 +278,8 @@ If you want to deploy Yi models, make sure you meet the [software and hardware r
|
|
311 |
<li>Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions.</li>
|
312 |
<li>Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc.</li>
|
313 |
<li>To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top_p, or top_k. These adjustments can help in the balance between creativity and coherence in the model's outputs.</li>
|
314 |
-
|
315 |
-
|
316 |
|
317 |
<p align="right"> [
|
318 |
<a href="#top">Back to top ⬆️ </a> ]
|
@@ -331,7 +298,6 @@ If you want to deploy Yi models, make sure you meet the [software and hardware r
|
|
331 |
- [Fine-tuning](#fine-tuning)
|
332 |
- [Quantization](#quantization)
|
333 |
- [Deployment](#deployment)
|
334 |
-
- [FAQ](#faq)
|
335 |
- [Learning hub](#learning-hub)
|
336 |
|
337 |
## Quick start
|
@@ -371,7 +337,7 @@ If you want to explore more features of Yi, you can adopt one of these methods:
|
|
371 |
##### 🙋♀️ Run Yi in playground
|
372 |
|
373 |
If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options:
|
374 |
-
|
375 |
- [Yi-34B-Chat-Playground](https://platform.lingyiwanwu.com/prompt/playground) (Yi official)
|
376 |
- Access is available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)).
|
377 |
|
@@ -396,7 +362,7 @@ If you want to chat with Yi with more customizable options (e.g., system prompt,
|
|
396 |
This tutorial guides you through every step of running **Yi-34B-Chat locally on an A800 (80G)** and then performing inference.
|
397 |
|
398 |
#### Step 0: Prerequisites
|
399 |
-
|
400 |
- Make sure Python 3.10 or a later version is installed.
|
401 |
|
402 |
- If you want to run other Yi models, see [software and hardware requirements](#deployment).
|
@@ -498,11 +464,11 @@ You can perform inference with Yi chat or base models as below.
|
|
498 |
|
499 |
```bash
|
500 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
501 |
-
|
502 |
MODEL_DIR = "01-ai/Yi-9B"
|
503 |
model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto")
|
504 |
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False)
|
505 |
-
|
506 |
input_text = "# write the quick sort algorithm"
|
507 |
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
|
508 |
outputs = model.generate(**inputs, max_length=256)
|
@@ -521,15 +487,14 @@ You can perform inference with Yi chat or base models as below.
|
|
521 |
middle = [x for x in arr if x == pivot]
|
522 |
right = [x for x in arr if x > pivot]
|
523 |
return quick_sort(left) + middle + quick_sort(right)
|
524 |
-
|
525 |
# test the quick sort algorithm
|
526 |
print(quick_sort([3, 6, 8, 10, 1, 2, 1]))
|
527 |
```
|
528 |
|
529 |
-
|
530 |
-
<
|
531 |
-
|
532 |
-
</p>
|
533 |
|
534 |
### Quick start - Docker
|
535 |
<details>
|
@@ -547,7 +512,7 @@ ghcr.io/01-ai/yi:latest
|
|
547 |
|
548 |
<h4>Step 2: Perform inference</h4>
|
549 |
<p>You can perform inference with Yi chat or base models as below.</p>
|
550 |
-
|
551 |
<h5>Perform inference with Yi chat model</h5>
|
552 |
<p>The steps are similar to <a href="#perform-inference-with-yi-chat-model">pip - Perform inference with Yi chat model</a>.</p>
|
553 |
<p><strong>Note</strong> that the only difference is to set <code>model_path = '<your-model-mount-path>'</code> instead of <code>model_path = '<your-model-path>'</code>.</p>
|
@@ -572,10 +537,9 @@ To install the dependencies, follow these steps:
|
|
572 |
|
573 |
|
574 |
### Quick start - llama.cpp
|
575 |
-
<a href="https://github.com/01-ai/Yi/blob/main/docs/README_llama.cpp.md">The following tutorial </a> will guide you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.
|
576 |
<details>
|
577 |
<summary> Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. ⬇️</summary>
|
578 |
-
<br
|
579 |
|
580 |
- [Step 0: Prerequisites](#step-0-prerequisites)
|
581 |
- [Step 1: Download llama.cpp](#step-1-download-llamacpp)
|
@@ -669,7 +633,7 @@ Now you have successfully asked a question to the Yi model and got an answer!
|
|
669 |
|
670 |
```bash
|
671 |
...
|
672 |
-
|
673 |
llama_new_context_with_model: n_ctx = 2048
|
674 |
llama_new_context_with_model: freq_base = 5000000.0
|
675 |
llama_new_context_with_model: freq_scale = 1
|
@@ -692,7 +656,7 @@ Now you have successfully asked a question to the Yi model and got an answer!
|
|
692 |
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67)
|
693 |
Available slots:
|
694 |
-> Slot 0 - max context: 2048
|
695 |
-
|
696 |
llama server listening at http://0.0.0.0:8080
|
697 |
```
|
698 |
|
@@ -794,11 +758,11 @@ pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sente
|
|
794 |
|
795 |
#### Hardware Setup
|
796 |
|
797 |
-
For the Yi-6B model, a node with 4 GPUs, each
|
798 |
|
799 |
-
For the Yi-34B model, because the usage of
|
800 |
|
801 |
-
A typical hardware setup for finetuning
|
802 |
|
803 |
#### Quick Start
|
804 |
|
@@ -881,12 +845,12 @@ python quantization/gptq/eval_quantized_model.py \
|
|
881 |
--trust_remote_code
|
882 |
```
|
883 |
|
884 |
-
<details style="display: inline;"><summary>For
|
885 |
|
886 |
#### GPT-Q quantization
|
887 |
|
888 |
-
[GPT-Q](https://github.com/IST-DASLab/gptq) is a PTQ
|
889 |
-
method. It
|
890 |
of the model.
|
891 |
|
892 |
Yi models can be GPT-Q quantized without a lot of efforts.
|
@@ -906,6 +870,7 @@ python quant_autogptq.py --model /base_model \
|
|
906 |
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
|
907 |
```
|
908 |
|
|
|
909 |
##### Run Quantized Model
|
910 |
|
911 |
You can run a quantized model using the `eval_quantized_model.py`:
|
@@ -917,7 +882,6 @@ python eval_quantized_model.py --model /quantized_model --trust_remote_code
|
|
917 |
</details>
|
918 |
|
919 |
#### AWQ
|
920 |
-
|
921 |
```bash
|
922 |
python quantization/awq/quant_autoawq.py \
|
923 |
--model /base_model \
|
@@ -932,11 +896,11 @@ python quantization/awq/eval_quantized_model.py \
|
|
932 |
--model /quantized_model \
|
933 |
--trust_remote_code
|
934 |
```
|
935 |
-
<details style="display: inline;"><summary>For
|
936 |
|
937 |
#### AWQ quantization
|
938 |
|
939 |
-
[AWQ](https://github.com/mit-han-lab/llm-awq) is a PTQ
|
940 |
method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs.
|
941 |
|
942 |
Yi models can be AWQ quantized without a lot of efforts.
|
@@ -1021,50 +985,12 @@ Below are detailed minimum VRAM requirements under different batch use cases.
|
|
1021 |
<a href="#top">Back to top ⬆️ </a> ]
|
1022 |
</p>
|
1023 |
|
1024 |
-
### FAQ
|
1025 |
-
<details>
|
1026 |
-
<summary> If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. ⬇️</summary>
|
1027 |
-
<br>
|
1028 |
-
|
1029 |
-
#### 💡Fine-tuning
|
1030 |
-
- <strong>Base model or Chat model - which to fine-tune?</strong>
|
1031 |
-
<br>The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task.
|
1032 |
-
- If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice.
|
1033 |
-
- On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice.
|
1034 |
-
- It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements.
|
1035 |
-
- <strong>Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?</strong>
|
1036 |
-
<br>
|
1037 |
-
The key distinction between full-scale fine-tuning on `Yi-34B`and `Yi-34B-Chat` comes down to the fine-tuning approach and outcomes.
|
1038 |
-
- Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely.
|
1039 |
-
- The Base model's fine-tuning is more versatile, with a relatively high performance potential.
|
1040 |
-
- If you are confident in the quality of your data, fine-tuning with `Yi-34B` could be your go-to.
|
1041 |
-
- If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, `Yi-34B-Chat` might be your best bet.
|
1042 |
-
|
1043 |
-
#### 💡Quantization
|
1044 |
-
- <strong>Quantized model versus original model - what is the performance gap?</strong>
|
1045 |
-
- The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points.
|
1046 |
-
- Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results.
|
1047 |
-
|
1048 |
-
#### 💡General
|
1049 |
-
- <strong>Where can I source fine-tuning question answering datasets?</strong>
|
1050 |
-
- You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like [m-a-p/COIG-CQIA](https://huggingface.co/datasets/m-a-p/COIG-CQIA) readily available.
|
1051 |
-
- Additionally, Github offers fine-tuning frameworks, such as [hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory), which integrates pre-made datasets.
|
1052 |
-
|
1053 |
-
- <strong>What is the GPU memory requirement for fine-tuning Yi-34B FP16?</strong>
|
1054 |
-
<br>
|
1055 |
-
The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out [hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory). Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance.
|
1056 |
-
|
1057 |
-
- <strong>Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?</strong>
|
1058 |
-
<br>
|
1059 |
-
If you're looking for third-party Chats, options include [fireworks.ai](https://fireworks.ai/login?callbackURL=https://fireworks.ai/models/fireworks/yi-34b-chat).
|
1060 |
-
</details>
|
1061 |
-
|
1062 |
### Learning hub
|
1063 |
|
1064 |
<details>
|
1065 |
<summary> If you want to learn Yi, you can find a wealth of helpful educational resources here. ⬇️</summary>
|
1066 |
<br>
|
1067 |
-
|
1068 |
Welcome to the Yi learning hub!
|
1069 |
|
1070 |
Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more.
|
@@ -1076,109 +1002,26 @@ At the same time, we also warmly invite you to join our collaborative effort by
|
|
1076 |
With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
|
1077 |
|
1078 |
#### Tutorials
|
1079 |
-
|
1080 |
-
|
1081 |
-
|
1082 |
-
|
|
1083 |
-
|
|
1084 |
-
| [
|
1085 |
-
| [
|
1086 |
-
|
1087 |
-
|
1088 |
-
|
1089 |
-
|
|
1090 |
-
|
1091 |
-
| [
|
1092 |
-
| [
|
1093 |
-
| [
|
1094 |
-
| [
|
1095 |
-
| [
|
1096 |
-
| [
|
1097 |
-
| [
|
1098 |
-
| [
|
1099 |
-
| [使用autodl服务器,两个3090显卡上运行, Yi-34B-Chat-int4模型,并使用vllm优化加速,显存占用42G,速度23 words-s](https://blog.csdn.net/freewebsys/article/details/134725765?ops_request_misc=%7B%22request%5Fid%22%3A%22171636356716800211598950%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636356716800211598950&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-9-134725765-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-04-27 | [fly-iot](https://gitee.com/fly-iot) |
|
1100 |
-
| [Getting Started with Yi-1.5-9B-Chat](https://www.secondstate.io/articles/yi-1.5-9b-chat/) | 2024-04-27 | [Second State](https://github.com/second-state) |
|
1101 |
-
| [基于零一万物yi-vl-plus大模型简单几步就能批量生成Anki图片笔记](https://mp.weixin.qq.com/s/_ea6g0pzzeO4WyYtuWycWQ) | 2024-04-24 | [正经人王同学](https://github.com/zjrwtx) |
|
1102 |
-
| [【AI开发:语言】一、Yi-34B超大模型本地部署CPU和GPU版](https://blog.csdn.net/alarey/article/details/137769471?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-16-137769471-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-04-21 | [My的梦想已实现](https://blog.csdn.net/alarey?type=blog) |
|
1103 |
-
| [【Yi-34B-Chat-Int4】使用4个2080Ti显卡11G版本,运行Yi-34B模型,5年前老显卡是支持的,可以正常运行,速度 21 words-s,vllm要求算力在7以上的显卡就可以](https://blog.csdn.net/freewebsys/article/details/134754086) | 2024-03-22 | [fly-iot](https://gitee.com/fly-iot) |
|
1104 |
-
| [零一万物大模型部署+微调总结](https://blog.csdn.net/v_wus/article/details/135704126?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-18-135704126-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-22 | [v_wus](https://blog.csdn.net/v_wus?type=blog) |
|
1105 |
-
| [零一万物Yi大模型vllm推理时Yi-34B或Yi-6bchat重复输出的解决方案](https://blog.csdn.net/qq_39667443/article/details/136028776?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-6-136028776-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-02 | [郝铠锋](https://blog.csdn.net/qq_39667443?type=blog) |
|
1106 |
-
| [Yi-34B微调训练](https://blog.csdn.net/lsjlnd/article/details/135336984?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-12-135336984-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-02 | [lsjlnd](https://blog.csdn.net/lsjlnd?type=blog) |
|
1107 |
-
| [实测零一万物Yi-VL多模态语言模型:能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) |
|
1108 |
-
| [零一万物开源Yi-VL多模态大模型,魔搭社区推理&微调最佳实践来啦!](https://zhuanlan.zhihu.com/p/680098411) | 2024-01-26 | [ModelScope](https://github.com/modelscope) |
|
1109 |
-
| [单卡 3 小时训练 Yi-6B 大模型 Agent:基于 Llama Factory 实战](https://zhuanlan.zhihu.com/p/678989191) | 2024-01-22 | [郑耀威](https://github.com/hiyouga) |
|
1110 |
-
| [零一科技Yi-34B Chat大模型环境搭建&推理](https://blog.csdn.net/zzq1989_/article/details/135597181?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-8-135597181-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-15 | [要养家的程序员](https://blog.csdn.net/zzq1989_?type=blog) |
|
1111 |
-
| [基于LLaMA Factory,单卡3小时训练专属大模型 Agent](https://blog.csdn.net/m0_59596990/article/details/135760285?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135760285-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-15 | [机器学习社区](https://blog.csdn.net/m0_59596990?type=blog) |
|
1112 |
-
| [双卡 3080ti 部署 Yi-34B 大模型 - Gradio + vLLM 踩坑全记录](https://blog.csdn.net/arkohut/article/details/135321242?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135321242-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-02 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1113 |
-
| [【大模型部署实践-3】3个能在3090上跑起来的4bits量化Chat模型(baichuan2-13b、InternLM-20b、Yi-34b)](https://blog.csdn.net/qq_40302568/article/details/135040985?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-30-135040985-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-02 | [aq_Seabiscuit](https://blog.csdn.net/qq_40302568?type=blog) |
|
1114 |
-
| [只需 24G 显存,用 vllm 跑起来 Yi-34B 中英双语大模型](https://blog.csdn.net/arkohut/article/details/135274973) | 2023-12-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1115 |
-
| [零一万物模型官方 Yi-34B 模型本地离线运行部署使用笔记(物理机和docker两种部署方式),200K 超长文本内容,34B 干翻一众 70B 模型,打榜分数那么高,这模型到底行不行?](https://blog.csdn.net/u014374009/article/details/136327696) | 2023-12-28 | [代码讲故事](https://blog.csdn.net/u014374009?type=blog) |
|
1116 |
-
| [LLM - 大模型速递之 Yi-34B 入门与 LoRA 微调](https://blog.csdn.net/BIT_666/article/details/134990402) | 2023-12-18 | [BIT_666](https://bitddd.blog.csdn.net/?type=blog) |
|
1117 |
-
| [通过vllm框架进行大模型推理](https://blog.csdn.net/weixin_45920955/article/details/135300561?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-13-135300561-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2023-12-18 | [土山炮](https://blog.csdn.net/weixin_45920955?type=blog) |
|
1118 |
-
| [CPU 混合推理,非常见大模型量化方案:“二三五六” 位量化方案](https://zhuanlan.zhihu.com/p/671698216) | 2023-12-12 | [苏洋](https://github.com/soulteary) |
|
1119 |
-
| [零一万物模型折腾笔记:官方 Yi-34B 模型基础使用](https://zhuanlan.zhihu.com/p/671387298) | 2023-12-10 | [苏洋](https://github.com/soulteary) |
|
1120 |
-
| [Running Yi-34B-Chat locally using LlamaEdge](https://www.secondstate.io/articles/yi-34b/) | 2023-11-30 | [Second State](https://github.com/second-state) |
|
1121 |
-
| [本地运行零一万物 34B 大模型,使用 Llama.cpp & 21G 显存](https://zhuanlan.zhihu.com/p/668921042) | 2023-11-26 | [苏洋](https://github.com/soulteary) |
|
1122 |
-
|
1123 |
-
##### GitHub Project
|
1124 |
-
|
1125 |
-
| Deliverable | Date | Author |
|
1126 |
-
| ------------------------------------------------------------ | ---------- | ------------------------------------------- |
|
1127 |
-
| [yi-openai-proxy](https://github.com/soulteary/yi-openai-proxy) | 2024-05-11 | [苏洋](https://github.com/soulteary) |
|
1128 |
-
| [基于零一万物 Yi 模型和 B 站构建大语言模型高质量训练数据集](https://github.com/zjrwtx/bilibiliQA_databuilder) | 2024-04-29 | [正经人王同学](https://github.com/zjrwtx) |
|
1129 |
-
| [基于视频网站和零一万物大模型构建大语言模型高质量训练数据集](https://github.com/zjrwtx/VideoQA_databuilder) | 2024-04-25 | [正经人王同学](https://github.com/zjrwtx) |
|
1130 |
-
| [基于零一万物yi-34b-chat-200k输入任意文章地址,点击按钮即可生成无广告或推广内容的简要笔记,并生成分享图给好友](https://github.com/zjrwtx/open_summary) | 2024-04-24 | [正经人王同学](https://github.com/zjrwtx) |
|
1131 |
-
| [Food-GPT-Yi-model](https://github.com/ThisisHubert/FoodGPT-Yi-model) | 2024-04-21 | [Hubert S](https://github.com/ThisisHubert) |
|
1132 |
-
|
1133 |
-
##### Video tutorials
|
1134 |
-
|
1135 |
-
| Deliverable | Date | Author |
|
1136 |
-
| ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ |
|
1137 |
-
| [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) |
|
1138 |
-
| [只需 24G 显存,用 vllm 跑起来 Yi-34B 中英双语大模型](https://www.bilibili.com/video/BV17t4y1f7Ee/) | 2023-12-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1139 |
-
| [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
|
1140 |
-
| [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) |
|
1141 |
-
| [Yi-VL-34B 多模态大模型 - 用两张 A40 显卡跑起来](https://www.bilibili.com/video/BV1Q5411y7AG/) | 2024-01-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1142 |
-
| [4060Ti 16G显卡安装零一万物最新开源的Yi-1.5版大语言模型](https://www.bilibili.com/video/BV16i421X7Jx/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-14 | [titan909](https://space.bilibili.com/526393761) |
|
1143 |
-
| [Yi-1.5: True Apache 2.0 Competitor to LLAMA-3](https://www.youtube.com/watch?v=KCDYrfWeTRc) | 2024-05-13 | [Prompt Engineering](https://www.youtube.com/@engineerprompt) |
|
1144 |
-
| [Install Yi-1.5 Model Locally - Beats Llama 3 in Various Benchmarks](https://www.youtube.com/watch?v=Ba-G7Il0UkA) | 2024-05-13 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
|
1145 |
-
| [how to install Ollama and run Yi 6B](https://www.youtube.com/watch?v=4Jnar7OUHqQ) | 2024-05-13 | [Ridaa Davids](https://www.youtube.com/@quantanovabusiness) |
|
1146 |
-
| [地表最强混合智能AI助手:llama3_70B+Yi_34B+Qwen1.5_110B](https://www.bilibili.com/video/BV1Xm411C7V1/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-04 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
|
1147 |
-
| [ChatDoc学术论文辅助--基于Yi-34B和langchain进行PDF知识库问答](https://www.bilibili.com/video/BV11i421C7B5/?spm_id_from=333.999.0.0&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-03 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
|
1148 |
-
| [基于Yi-34B的领域知识问答项目演示](https://www.bilibili.com/video/BV1zZ42177ZA/?spm_id_from=333.999.0.0&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-02 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
|
1149 |
-
| [使用RTX4090+GaLore算法 全参微调Yi-6B大模型](https://www.bilibili.com/video/BV1ax4y1U7Ep/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-03-24 | [小工蚂创始人](https://space.bilibili.com/478674499?spm_id_from=333.788.0.0) |
|
1150 |
-
| [无内容审查NSFW大语言模型Yi-34B-Chat蒸馏版测试,RolePlay,《天龙八部》马夫人康敏,本地GPU,CPU运行](https://www.youtube.com/watch?v=VL-W0TnLCns) | 2024-03-20 | [刘悦的技术博客](https://v3u.cn/) |
|
1151 |
-
| [无内容审查NSFW大语言模型整合包,Yi-34B-Chat,本地CPU运行,角色扮演潘金莲](https://www.youtube.com/watch?v=rBvbgwz3oHM) | 2024-03-16 | [刘悦的技术博客](https://v3u.cn/) |
|
1152 |
-
| [量化 Yi-34B-Chat 并在单卡 RTX 4090 使用 vLLM 部署](https://www.bilibili.com/video/BV1jx421y7xj/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-03-05 | [白鸽巢](https://space.bilibili.com/138938660?spm_id_from=333.788.0.0) |
|
1153 |
-
| [Yi-VL-34B(5):使用3个3090显卡24G版本,运行Yi-VL-34B模型,支持命令行和web界面方式,理解图片的内容转换成文字](https://www.bilibili.com/video/BV1BB421z7oA/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-27 | [fly-iot](https://gitee.com/fly-iot) |
|
1154 |
-
| [Win环境KoboldCpp本地部署大语言模型进行各种角色扮演游戏](https://www.bilibili.com/video/BV14J4m1e77f/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-25 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
|
1155 |
-
| [无需显卡本地部署Yi-34B-Chat进行角色扮演游戏 P2](https://www.bilibili.com/video/BV19v421677y/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-23 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
|
1156 |
-
| [【wails】(2):使用go-llama.cpp 运行 yi-01-6b大模型,使用本地CPU运行,速度还可以,等待下一版本更新](https://www.bilibili.com/video/BV194421F7Fy/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-20 | [fly-iot](https://gitee.com/fly-iot) |
|
1157 |
-
| [【xinference】(6):在autodl上,使用xinference部署yi-vl-chat和qwen-vl-chat模型,可以使用openai调用成功](https://www.bilibili.com/video/BV19Z421z7cv/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-06 | [fly-iot](https://gitee.com/fly-iot) |
|
1158 |
-
| [无需显卡本地部署Yi-34B-Chat进行角色扮演游戏 P1](https://www.bilibili.com/video/BV1tU421o7Co/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-05 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
|
1159 |
-
| [2080Ti部署YI-34B大模型 xinference-oneapi-fastGPT本地知识库使用指南](https://www.bilibili.com/video/BV1hC411z7xu/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-30 | [小饭护法要转码](https://space.bilibili.com/39486865?spm_id_from=333.788.0.0) |
|
1160 |
-
| [Best Story Writing AI Model - Install Yi 6B 200K Locally on Windows](https://www.youtube.com/watch?v=cZs2jRtl0bs) | 2024-01-22 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
|
1161 |
-
| [Mac 本地运行大语言模型方法与常见问题指南(Yi 34B 模型+32 GB 内存测试)](https://www.bilibili.com/video/BV1VT4y1b7Th/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-21 | [小吴苹果机器人](https://space.bilibili.com/1732749682?spm_id_from=333.788.0.0) |
|
1162 |
-
| [【Dify知识库】(11):Dify0.4.9改造支持MySQL,成功接入yi-6b 做对话,本地使用fastchat启动,占8G显存,完成知识库配置](https://www.bilibili.com/video/BV1ia4y1y7JH/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-21 | [fly-iot](https://gitee.com/fly-iot) |
|
1163 |
-
| [这位LLM先生有点暴躁,用的是YI-6B的某个量化版,#LLM #大语言模型 #暴躁老哥](https://www.youtube.com/watch?v=eahXJrdtQuc) | 2024-01-20 | [晓漫吧](https://www.youtube.com/@xiaomanba) |
|
1164 |
-
| [大模型推理 NvLink 桥接器有用吗|双卡 A6000 测试一下](https://www.bilibili.com/video/BV1AW4y1w7DC/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-17 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1165 |
-
| [大模型推理 A40 vs A6000 谁更强 - 对比 Yi-34B 的单、双卡推理性能](https://www.bilibili.com/video/BV1aK4y1z7GF/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-15 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1166 |
-
| [C-Eval 大语言模型评测基准- 用 LM Evaluation Harness + vLLM 跑起来](https://www.bilibili.com/video/BV1Yw411g7ZL/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-11 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1167 |
-
| [双显卡部署 Yi-34B 大模型 - vLLM + Gradio 踩坑记录](https://www.bilibili.com/video/BV1p94y1c7ak/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-01 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1168 |
-
| [手把手教学!使用 vLLM 快速部署 Yi-34B-Chat](https://www.bilibili.com/video/BV1ew41157Mk/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-26 | [白鸽巢](https://space.bilibili.com/138938660?spm_id_from=333.788.0.0) |
|
1169 |
-
| [如何训练企业自己的大语言模型?Yi-6B LORA微调演示 #小工蚁](https://www.bilibili.com/video/BV1uc41117zz/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-21 | [小工蚂创始人](https://space.bilibili.com/478674499?spm_id_from=333.788.0.0) |
|
1170 |
-
| [Yi-34B(4):使用4个2080Ti显卡11G版本,运行Yi-34B模型,5年前老显卡是支持的,可以正常运行,速度 21 words/s](https://www.bilibili.com/video/BV1nj41157L3/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-02 | [fly-iot](https://gitee.com/fly-iot) |
|
1171 |
-
| [使用autodl服务器,RTX 3090 * 3 显卡上运行, Yi-34B-Chat模型,显存占用60G](https://www.bilibili.com/video/BV1BM411R7ae/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [fly-iot](https://gitee.com/fly-iot) |
|
1172 |
-
| [使用autodl服务器,两个3090显卡上运行, Yi-34B-Chat-int4模型,用vllm优化,增加 --num-gpu 2,速度23 words/s](https://www.bilibili.com/video/BV1Hu4y1L7BH/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [fly-iot](https://gitee.com/fly-iot) |
|
1173 |
-
| [Yi大模型一键本地部署 技术小白玩转AI](https://www.bilibili.com/video/BV16H4y117md/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [技术小白玩转AI](https://space.bilibili.com/3546586137234288?spm_id_from=333.788.0.0) |
|
1174 |
-
| [01.AI's Yi-6B: Overview and Fine-Tuning](https://www.youtube.com/watch?v=mye-UOkAliQ) | 2023-11-28 | [AI Makerspace](https://www.youtube.com/@AI-Makerspace) |
|
1175 |
-
| [Yi 34B Chat LLM outperforms Llama 70B](https://www.youtube.com/watch?v=RYtrF-R5jDc) | 2023-11-27 | [DLExplorer](https://www.youtube.com/@DLExplorers-lg7dt) |
|
1176 |
-
| [How to run open source models on mac Yi 34b on m3 Max](https://www.youtube.com/watch?v=GAo-dopkgjI) | 2023-11-26 | [TECHNO PREMIUM](https://www.youtube.com/@technopremium91) |
|
1177 |
-
| [Yi-34B - 200K - The BEST & NEW CONTEXT WINDOW KING ](https://www.youtube.com/watch?v=7WBojwwv5Qo) | 2023-11-24 | [Prompt Engineering](https://www.youtube.com/@engineerprompt) |
|
1178 |
-
| [Yi 34B : The Rise of Powerful Mid-Sized Models - Base,200k & Chat](https://www.youtube.com/watch?v=bWCjwtu_tHs) | 2023-11-24 | [Sam Witteveen](https://www.youtube.com/@samwitteveenai) |
|
1179 |
-
| [在IoT设备运行破解版李开复大模型dolphin-2.2-yi-34b(还可作为私有OpenAI API服务器)](https://www.bilibili.com/video/BV1SQ4y18744/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-11-15 | [Second State](https://github.com/second-state) |
|
1180 |
-
| [Run dolphin-2.2-yi-34b on IoT Devices (Also works as a Private OpenAI API Server)](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-14 | [Second State](https://github.com/second-state) |
|
1181 |
-
| [How to Install Yi 34B 200K Llamafied on Windows Laptop](https://www.youtube.com/watch?v=enoha4K4HkQ) | 2023-11-11 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
|
1182 |
|
1183 |
</details>
|
1184 |
|
@@ -1197,7 +1040,7 @@ With all these resources at your fingertips, you're ready to start your exciting
|
|
1197 |
- [Base model performance](#base-model-performance)
|
1198 |
- [Yi-34B and Yi-34B-200K](#yi-34b-and-yi-34b-200k)
|
1199 |
- [Yi-9B](#yi-9b)
|
1200 |
-
|
1201 |
## Ecosystem
|
1202 |
|
1203 |
Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity.
|
@@ -1302,8 +1145,8 @@ For detailed capabilities of the Yi series model, see [Yi: Open Foundation Model
|
|
1302 |
|
1303 |
## Benchmarks
|
1304 |
|
1305 |
-
- [Chat model performance](
|
1306 |
-
- [Base model performance](
|
1307 |
|
1308 |
### Chat model performance
|
1309 |
|
@@ -1350,19 +1193,19 @@ Yi-9B is almost the best among a range of similar-sized open-source models (incl
|
|
1350 |
|
1351 |
- In terms of **overall** ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B.
|
1352 |
|
1353 |
-
|
1354 |
|
1355 |
- In terms of **coding** ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B.
|
1356 |
|
1357 |
-
|
1358 |
|
1359 |
- In terms of **math** ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B.
|
1360 |
|
1361 |
-
|
1362 |
|
1363 |
- In terms of **common sense and reasoning** ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B.
|
1364 |
|
1365 |
-
|
1366 |
|
1367 |
<p align="right"> [
|
1368 |
<a href="#top">Back to top ⬆️ </a> ]
|
@@ -1372,7 +1215,9 @@ Yi-9B is almost the best among a range of similar-sized open-source models (incl
|
|
1372 |
|
1373 |
Everyone! 🙌 ✅
|
1374 |
|
1375 |
-
The
|
|
|
|
|
1376 |
|
1377 |
<p align="right"> [
|
1378 |
<a href="#top">Back to top ⬆️ </a> ]
|
@@ -1407,13 +1252,10 @@ as well as any associated data security concerns.
|
|
1407 |
|
1408 |
### License
|
1409 |
|
1410 |
-
The code
|
1411 |
-
|
1412 |
-
|
1413 |
-
|
1414 |
-
This work is a derivative of [The Yi Series Model You Base On] by 01.AI, used under the Apache 2.0 License.
|
1415 |
|
1416 |
<p align="right"> [
|
1417 |
<a href="#top">Back to top ⬆️ </a> ]
|
1418 |
</p>
|
1419 |
-
|
|
|
1 |
---
|
2 |
+
license: other
|
3 |
+
license_name: yi-license
|
4 |
+
license_link: LICENSE
|
5 |
widget:
|
6 |
- example_title: "Yi-34B-Chat"
|
7 |
text: "hi"
|
|
|
31 |
</a>
|
32 |
</div>
|
33 |
|
34 |
+
<div style="display: inline-block;">
|
35 |
+
<a href="https://github.com/01-ai/Yi/blob/main/LICENSE">
|
36 |
+
<img src="https://img.shields.io/badge/Code_License-Apache_2.0-lightblue">
|
37 |
+
</a>
|
38 |
+
</div>
|
39 |
+
|
40 |
+
<div style="display: inline-block;">
|
41 |
+
<a href="https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt">
|
42 |
+
<img src="https://img.shields.io/badge/Model_License-Yi_License-lightblue">
|
43 |
+
</a>
|
44 |
+
</div>
|
45 |
+
|
46 |
<div style="display: inline-block;">
|
47 |
<a href="mailto:oss@01.ai">
|
48 |
<img src="https://img.shields.io/badge/✉️-yi@01.ai-FFE01B">
|
|
|
60 |
</p>
|
61 |
|
62 |
<p align="center">
|
63 |
+
👋 Join us 💬 <a href="https://github.com/01-ai/Yi/issues/43#issuecomment-1827285245" target="_blank"> WeChat (Chinese) </a>!
|
64 |
</p>
|
65 |
|
|
|
|
|
|
|
66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
<!-- DO NOT REMOVE ME -->
|
68 |
|
69 |
<hr>
|
|
|
76 |
- [Models](#models)
|
77 |
- [Chat models](#chat-models)
|
78 |
- [Base models](#base-models)
|
79 |
+
- [Other info](#other-info)
|
80 |
- [News](#news)
|
81 |
- [How to use Yi?](#how-to-use-yi)
|
82 |
- [Quick start](#quick-start)
|
|
|
89 |
- [Fine-tuning](#fine-tuning)
|
90 |
- [Quantization](#quantization)
|
91 |
- [Deployment](#deployment)
|
|
|
92 |
- [Learning hub](#learning-hub)
|
93 |
- [Why Yi?](#why-yi)
|
94 |
- [Ecosystem](#ecosystem)
|
|
|
122 |
- 🙌 Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example,
|
123 |
|
124 |
- Yi-34B-Chat model **landed in second place (following GPT-4 Turbo)**, outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024).
|
125 |
+
|
126 |
- Yi-34B model **ranked first among all existing open-source models** (such as Falcon-180B, Llama-70B, Claude) in **both English and Chinese** on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023).
|
127 |
|
128 |
- 🙏 (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem.
|
129 |
|
130 |
<details style="display: inline;"><summary> If you're interested in Yi's adoption of Llama architecture and license usage policy, see <span style="color: green;">Yi's relation with Llama.</span> ⬇️</summary> <ul> <br>
|
131 |
|
|
|
132 |
> 💡 TL;DR
|
133 |
>
|
134 |
> The Yi series models adopt the same model architecture as Llama but are **NOT** derivatives of Llama.
|
|
|
153 |
|
154 |
## News
|
155 |
|
156 |
+
<details open>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
<summary>🎯 <b>2024-03-08</b>: <a href="https://arxiv.org/abs/2403.04652">Yi Tech Report</a> is published! </summary>
|
158 |
</details>
|
159 |
|
|
|
232 |
|
233 |
### Chat models
|
234 |
|
235 |
+
| Model | Download
|
236 |
+
|---|---
|
237 |
+
Yi-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat/summary)
|
238 |
+
Yi-34B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-4bits/summary)
|
239 |
+
Yi-34B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-8bits/summary)
|
240 |
+
Yi-6B-Chat| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat/summary)
|
241 |
+
Yi-6B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-4bits/summary)
|
242 |
+
Yi-6B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-8bits/summary)
|
243 |
+
|
244 |
|
245 |
<sub><sup> - 4-bit series models are quantized by AWQ. <br> - 8-bit series models are quantized by GPTQ <br> - All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). </sup></sub>
|
246 |
|
247 |
### Base models
|
248 |
|
249 |
+
| Model | Download |
|
250 |
|---|---|
|
251 |
+
Yi-34B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B/summary)
|
252 |
+
Yi-34B-200K|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-200K/summary)
|
253 |
+
Yi-9B|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-9B)
|
254 |
+
Yi-9B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-9B-200K)
|
255 |
+
Yi-6B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B/summary)
|
256 |
+
Yi-6B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-200K/summary)
|
257 |
|
258 |
<sub><sup> - 200k is roughly equivalent to 400,000 Chinese characters. <br> - If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run `git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf` to download the weight. </sup></sub>
|
259 |
|
|
|
261 |
|
262 |
- For chat and base models
|
263 |
|
264 |
+
Model | Intro | Default context window | Pretrained tokens | Training Data Date
|
265 |
+
|---|---|---|---|---
|
266 |
+
6B series models |They are suitable for personal and academic use. | 4K | 3T | Up to June 2023
|
267 |
+
9B model| It is the best at coding and math in the Yi series models.|4K | Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. | Up to June 2023
|
268 |
+
34B series models | They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability.|4K | 3T | Up to June 2023
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
269 |
|
270 |
- For chat models
|
271 |
|
|
|
278 |
<li>Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions.</li>
|
279 |
<li>Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc.</li>
|
280 |
<li>To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top_p, or top_k. These adjustments can help in the balance between creativity and coherence in the model's outputs.</li>
|
281 |
+
</ul>
|
282 |
+
</details>
|
283 |
|
284 |
<p align="right"> [
|
285 |
<a href="#top">Back to top ⬆️ </a> ]
|
|
|
298 |
- [Fine-tuning](#fine-tuning)
|
299 |
- [Quantization](#quantization)
|
300 |
- [Deployment](#deployment)
|
|
|
301 |
- [Learning hub](#learning-hub)
|
302 |
|
303 |
## Quick start
|
|
|
337 |
##### 🙋♀️ Run Yi in playground
|
338 |
|
339 |
If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options:
|
340 |
+
|
341 |
- [Yi-34B-Chat-Playground](https://platform.lingyiwanwu.com/prompt/playground) (Yi official)
|
342 |
- Access is available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)).
|
343 |
|
|
|
362 |
This tutorial guides you through every step of running **Yi-34B-Chat locally on an A800 (80G)** and then performing inference.
|
363 |
|
364 |
#### Step 0: Prerequisites
|
365 |
+
|
366 |
- Make sure Python 3.10 or a later version is installed.
|
367 |
|
368 |
- If you want to run other Yi models, see [software and hardware requirements](#deployment).
|
|
|
464 |
|
465 |
```bash
|
466 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
467 |
+
|
468 |
MODEL_DIR = "01-ai/Yi-9B"
|
469 |
model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto")
|
470 |
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False)
|
471 |
+
|
472 |
input_text = "# write the quick sort algorithm"
|
473 |
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
|
474 |
outputs = model.generate(**inputs, max_length=256)
|
|
|
487 |
middle = [x for x in arr if x == pivot]
|
488 |
right = [x for x in arr if x > pivot]
|
489 |
return quick_sort(left) + middle + quick_sort(right)
|
490 |
+
|
491 |
# test the quick sort algorithm
|
492 |
print(quick_sort([3, 6, 8, 10, 1, 2, 1]))
|
493 |
```
|
494 |
|
495 |
+
<p align="right"> [
|
496 |
+
<a href="#top">Back to top ⬆️ </a> ]
|
497 |
+
</p>
|
|
|
498 |
|
499 |
### Quick start - Docker
|
500 |
<details>
|
|
|
512 |
|
513 |
<h4>Step 2: Perform inference</h4>
|
514 |
<p>You can perform inference with Yi chat or base models as below.</p>
|
515 |
+
|
516 |
<h5>Perform inference with Yi chat model</h5>
|
517 |
<p>The steps are similar to <a href="#perform-inference-with-yi-chat-model">pip - Perform inference with Yi chat model</a>.</p>
|
518 |
<p><strong>Note</strong> that the only difference is to set <code>model_path = '<your-model-mount-path>'</code> instead of <code>model_path = '<your-model-path>'</code>.</p>
|
|
|
537 |
|
538 |
|
539 |
### Quick start - llama.cpp
|
|
|
540 |
<details>
|
541 |
<summary> Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. ⬇️</summary>
|
542 |
+
<br>This tutorial guides you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.</p>
|
543 |
|
544 |
- [Step 0: Prerequisites](#step-0-prerequisites)
|
545 |
- [Step 1: Download llama.cpp](#step-1-download-llamacpp)
|
|
|
633 |
|
634 |
```bash
|
635 |
...
|
636 |
+
|
637 |
llama_new_context_with_model: n_ctx = 2048
|
638 |
llama_new_context_with_model: freq_base = 5000000.0
|
639 |
llama_new_context_with_model: freq_scale = 1
|
|
|
656 |
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67)
|
657 |
Available slots:
|
658 |
-> Slot 0 - max context: 2048
|
659 |
+
|
660 |
llama server listening at http://0.0.0.0:8080
|
661 |
```
|
662 |
|
|
|
758 |
|
759 |
#### Hardware Setup
|
760 |
|
761 |
+
For the Yi-6B model, a node with 4 GPUs, each has GPU mem larger than 60GB is recommended.
|
762 |
|
763 |
+
For the Yi-34B model, because the usage of zero-offload technique takes a lot CPU memory, please be careful to limit the GPU numbers in 34B finetune training. Please use CUDA_VISIBLE_DEVICES to limit the GPU number (as shown in scripts/run_sft_Yi_34b.sh).
|
764 |
|
765 |
+
A typical hardware setup for finetuning 34B model is a node with 8GPUS (limit to 4 in running by CUDA_VISIBLE_DEVICES=0,1,2,3), each has GPU mem larger than 80GB, with total CPU mem larger than 900GB.
|
766 |
|
767 |
#### Quick Start
|
768 |
|
|
|
845 |
--trust_remote_code
|
846 |
```
|
847 |
|
848 |
+
<details style="display: inline;"><summary>For a more detailed explanation, see the explanations below. ⬇️</summary> <ul>
|
849 |
|
850 |
#### GPT-Q quantization
|
851 |
|
852 |
+
[GPT-Q](https://github.com/IST-DASLab/gptq) is a PTQ(Post-Training Quantization)
|
853 |
+
method. It's memory saving and provides potential speedups while retaining the accuracy
|
854 |
of the model.
|
855 |
|
856 |
Yi models can be GPT-Q quantized without a lot of efforts.
|
|
|
870 |
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
|
871 |
```
|
872 |
|
873 |
+
|
874 |
##### Run Quantized Model
|
875 |
|
876 |
You can run a quantized model using the `eval_quantized_model.py`:
|
|
|
882 |
</details>
|
883 |
|
884 |
#### AWQ
|
|
|
885 |
```bash
|
886 |
python quantization/awq/quant_autoawq.py \
|
887 |
--model /base_model \
|
|
|
896 |
--model /quantized_model \
|
897 |
--trust_remote_code
|
898 |
```
|
899 |
+
<details style="display: inline;"><summary>For detailed explanations, see the explanations below. ⬇️</summary> <ul>
|
900 |
|
901 |
#### AWQ quantization
|
902 |
|
903 |
+
[AWQ](https://github.com/mit-han-lab/llm-awq) is a PTQ(Post-Training Quantization)
|
904 |
method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs.
|
905 |
|
906 |
Yi models can be AWQ quantized without a lot of efforts.
|
|
|
985 |
<a href="#top">Back to top ⬆️ </a> ]
|
986 |
</p>
|
987 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
988 |
### Learning hub
|
989 |
|
990 |
<details>
|
991 |
<summary> If you want to learn Yi, you can find a wealth of helpful educational resources here. ⬇️</summary>
|
992 |
<br>
|
993 |
+
|
994 |
Welcome to the Yi learning hub!
|
995 |
|
996 |
Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more.
|
|
|
1002 |
With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
|
1003 |
|
1004 |
#### Tutorials
|
1005 |
+
##### English tutorials
|
1006 |
+
| Type | Deliverable | Date | Author |
|
1007 |
+
|-------------|--------------------------------------------------------|----------------|----------------|
|
1008 |
+
| Video | [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) |
|
1009 |
+
| Blog | [Running Yi-34B-Chat locally using LlamaEdge](https://www.secondstate.io/articles/yi-34b/) | 2023-11-30 | [Second State](https://github.com/second-state) |
|
1010 |
+
| Video | [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
|
1011 |
+
| Video | [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) |
|
1012 |
+
|
1013 |
+
|
1014 |
+
##### Chinese tutorials
|
1015 |
+
| Type | Deliverable | Date | Author |
|
1016 |
+
|-------------|--------------------------------------------------------|----------------|----------------|
|
1017 |
+
| Blog | [实测零一万物Yi-VL多模态语言模型:能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) |
|
1018 |
+
| Blog | [本地运行零一万物 34B 大模型,使用 Llama.cpp & 21G 显存](https://zhuanlan.zhihu.com/p/668921042) | 2023-11-26 | [苏洋](https://github.com/soulteary) |
|
1019 |
+
| Blog | [零一万物模型折腾笔记:官方 Yi-34B 模型基础使用](https://zhuanlan.zhihu.com/p/671387298) | 2023-12-10 | [苏洋](https://github.com/soulteary) |
|
1020 |
+
| Blog | [CPU 混合推理,非常见大模型量化方案:“二三五六” 位量化方案](https://zhuanlan.zhihu.com/p/671698216) | 2023-12-12 | [苏洋](https://github.com/soulteary) |
|
1021 |
+
| Blog | [单卡 3 小时训练 Yi-6B 大模型 Agent:基于 Llama Factory 实战](https://zhuanlan.zhihu.com/p/678989191) | 2024-01-22 | [郑耀威](https://github.com/hiyouga) |
|
1022 |
+
| Blog | [零一万物开源Yi-VL多模态大模型,魔搭社区推理&微调最佳实践来啦!](https://zhuanlan.zhihu.com/p/680098411) | 2024-01-26 | [ModelScope](https://github.com/modelscope) |
|
1023 |
+
| Video | [只需 24G 显存,用 vllm 跑起来 Yi-34B 中英双语大模型](https://www.bilibili.com/video/BV17t4y1f7Ee/) | 2023-12-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
1024 |
+
| Video | [Yi-VL-34B 多模态大模型 - 用两张 A40 显卡跑起来](https://www.bilibili.com/video/BV1Q5411y7AG/) | 2023-01-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1025 |
|
1026 |
</details>
|
1027 |
|
|
|
1040 |
- [Base model performance](#base-model-performance)
|
1041 |
- [Yi-34B and Yi-34B-200K](#yi-34b-and-yi-34b-200k)
|
1042 |
- [Yi-9B](#yi-9b)
|
1043 |
+
|
1044 |
## Ecosystem
|
1045 |
|
1046 |
Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity.
|
|
|
1145 |
|
1146 |
## Benchmarks
|
1147 |
|
1148 |
+
- [Chat model performance](#-chat-model-performance)
|
1149 |
+
- [Base model performance](#-base-model-performance)
|
1150 |
|
1151 |
### Chat model performance
|
1152 |
|
|
|
1193 |
|
1194 |
- In terms of **overall** ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B.
|
1195 |
|
1196 |
+
![Yi-9B benchmark - overall](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_overall.png?raw=true)
|
1197 |
|
1198 |
- In terms of **coding** ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B.
|
1199 |
|
1200 |
+
![Yi-9B benchmark - code](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_code.png?raw=true)
|
1201 |
|
1202 |
- In terms of **math** ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B.
|
1203 |
|
1204 |
+
![Yi-9B benchmark - math](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_math.png?raw=true)
|
1205 |
|
1206 |
- In terms of **common sense and reasoning** ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B.
|
1207 |
|
1208 |
+
![Yi-9B benchmark - text](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_text.png?raw=true)
|
1209 |
|
1210 |
<p align="right"> [
|
1211 |
<a href="#top">Back to top ⬆️ </a> ]
|
|
|
1215 |
|
1216 |
Everyone! 🙌 ✅
|
1217 |
|
1218 |
+
- The Yi series models are free for personal usage, academic purposes, and commercial use. All usage must adhere to the [Yi Series Models Community License Agreement 2.1](https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt)
|
1219 |
+
|
1220 |
+
- For free commercial use, you only need to [complete this form](https://www.lingyiwanwu.com/yi-license) to get a Yi Model Commercial License.
|
1221 |
|
1222 |
<p align="right"> [
|
1223 |
<a href="#top">Back to top ⬆️ </a> ]
|
|
|
1252 |
|
1253 |
### License
|
1254 |
|
1255 |
+
The source code in this repo is licensed under the [Apache 2.0
|
1256 |
+
license](https://github.com/01-ai/Yi/blob/main/LICENSE). The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the [Yi Series Models Community License Agreement 2.1](https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt).
|
1257 |
+
For free commercial use, you only need to send an email to [get official commercial permission](https://www.lingyiwanwu.com/yi-license).
|
|
|
|
|
1258 |
|
1259 |
<p align="right"> [
|
1260 |
<a href="#top">Back to top ⬆️ </a> ]
|
1261 |
</p>
|
|
images/initail.png
DELETED
Binary file (83.4 kB)
|
|
images/v20240318.png
DELETED
Binary file (82.7 kB)
|
|
images/v20240321.png
DELETED
Binary file (84.8 kB)
|
|
md5
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
291724ef50f729e45d68f474a7755bbc tokenizer.model
|
|
|
1 |
+
dbdb0057bd6a45b21ac8a708b11b5ca1 model-00001-of-00004.safetensors
|
2 |
+
8c21c8c0ec4642a5c957de7141c9dd6b model-00002-of-00004.safetensors
|
3 |
+
f30b358297910e8020ff9e19ac134a3e model-00003-of-00004.safetensors
|
4 |
+
f5f61561920649a6d2027b6a3956d3ec model-00004-of-00004.safetensors
|
5 |
291724ef50f729e45d68f474a7755bbc tokenizer.model
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932711424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:818de78b599ddb5c08c7fc9fa7752f6b976775bfcbc8f70babcb7e72ccc70b88
|
3 |
size 4932711424
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976802816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fd639f136ef2891625249e229f1195bea32a37c1aca6c0e1c4e9a7291d2ba75
|
3 |
size 4976802816
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4968397360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b52b1668f77e1219b6dee19a502a369abab33bf2746fd9e8c737f1740ad15fba
|
3 |
size 4968397360
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2780953384
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9805a8c571c22dd4f6c118bab0d2119740fbfedc29dc0286adb52af5c60126a1
|
3 |
size 2780953384
|
tokenizer.json
CHANGED
@@ -29,2067 +29,6 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 6,
|
35 |
-
"content": "<|im_start|>",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"special": true
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"id": 7,
|
44 |
-
"content": "<|im_end|>",
|
45 |
-
"single_word": false,
|
46 |
-
"lstrip": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
{
|
52 |
-
"id": 8,
|
53 |
-
"content": "<|im_sep|>",
|
54 |
-
"single_word": false,
|
55 |
-
"lstrip": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"id": 14,
|
62 |
-
"content": "<fim_prefix>",
|
63 |
-
"single_word": false,
|
64 |
-
"lstrip": false,
|
65 |
-
"rstrip": false,
|
66 |
-
"normalized": false,
|
67 |
-
"special": true
|
68 |
-
},
|
69 |
-
{
|
70 |
-
"id": 15,
|
71 |
-
"content": "<fim_middle>",
|
72 |
-
"single_word": false,
|
73 |
-
"lstrip": false,
|
74 |
-
"rstrip": false,
|
75 |
-
"normalized": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
{
|
79 |
-
"id": 16,
|
80 |
-
"content": "<fim_suffix>",
|
81 |
-
"single_word": false,
|
82 |
-
"lstrip": false,
|
83 |
-
"rstrip": false,
|
84 |
-
"normalized": false,
|
85 |
-
"special": true
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"id": 16,
|
89 |
-
"content": "<fim_suffix>",
|
90 |
-
"single_word": false,
|
91 |
-
"lstrip": false,
|
92 |
-
"rstrip": false,
|
93 |
-
"normalized": false,
|
94 |
-
"special": true
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"id": 17,
|
98 |
-
"content": "<fim_pad>",
|
99 |
-
"single_word": false,
|
100 |
-
"lstrip": false,
|
101 |
-
"rstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"special": true
|
104 |
-
},
|
105 |
-
{
|
106 |
-
"id": 18,
|
107 |
-
"content": "<filename>",
|
108 |
-
"single_word": false,
|
109 |
-
"lstrip": false,
|
110 |
-
"rstrip": false,
|
111 |
-
"normalized": false,
|
112 |
-
"special": true
|
113 |
-
},
|
114 |
-
{
|
115 |
-
"id": 19,
|
116 |
-
"content": "<gh_stars>",
|
117 |
-
"single_word": false,
|
118 |
-
"lstrip": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"normalized": false,
|
121 |
-
"special": true
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"id": 20,
|
125 |
-
"content": "<issue_start>",
|
126 |
-
"single_word": false,
|
127 |
-
"lstrip": false,
|
128 |
-
"rstrip": false,
|
129 |
-
"normalized": false,
|
130 |
-
"special": true
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"id": 21,
|
134 |
-
"content": "<issue_comment>",
|
135 |
-
"single_word": false,
|
136 |
-
"lstrip": false,
|
137 |
-
"rstrip": false,
|
138 |
-
"normalized": false,
|
139 |
-
"special": true
|
140 |
-
},
|
141 |
-
{
|
142 |
-
"id": 22,
|
143 |
-
"content": "<issue_closed>",
|
144 |
-
"single_word": false,
|
145 |
-
"lstrip": false,
|
146 |
-
"rstrip": false,
|
147 |
-
"normalized": false,
|
148 |
-
"special": true
|
149 |
-
},
|
150 |
-
{
|
151 |
-
"id": 23,
|
152 |
-
"content": "<jupyter_start>",
|
153 |
-
"single_word": false,
|
154 |
-
"lstrip": false,
|
155 |
-
"rstrip": false,
|
156 |
-
"normalized": false,
|
157 |
-
"special": true
|
158 |
-
},
|
159 |
-
{
|
160 |
-
"id": 24,
|
161 |
-
"content": "<jupyter_text>",
|
162 |
-
"single_word": false,
|
163 |
-
"lstrip": false,
|
164 |
-
"rstrip": false,
|
165 |
-
"normalized": false,
|
166 |
-
"special": true
|
167 |
-
},
|
168 |
-
{
|
169 |
-
"id": 25,
|
170 |
-
"content": "<jupyter_code>",
|
171 |
-
"single_word": false,
|
172 |
-
"lstrip": false,
|
173 |
-
"rstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"special": true
|
176 |
-
},
|
177 |
-
{
|
178 |
-
"id": 26,
|
179 |
-
"content": "<jupyter_output>",
|
180 |
-
"single_word": false,
|
181 |
-
"lstrip": false,
|
182 |
-
"rstrip": false,
|
183 |
-
"normalized": false,
|
184 |
-
"special": true
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"id": 27,
|
188 |
-
"content": "<empty_output>",
|
189 |
-
"single_word": false,
|
190 |
-
"lstrip": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"normalized": false,
|
193 |
-
"special": true
|
194 |
-
},
|
195 |
-
{
|
196 |
-
"id": 28,
|
197 |
-
"content": "<commit_before>",
|
198 |
-
"single_word": false,
|
199 |
-
"lstrip": false,
|
200 |
-
"rstrip": false,
|
201 |
-
"normalized": false,
|
202 |
-
"special": true
|
203 |
-
},
|
204 |
-
{
|
205 |
-
"id": 29,
|
206 |
-
"content": "<commit_msg>",
|
207 |
-
"single_word": false,
|
208 |
-
"lstrip": false,
|
209 |
-
"rstrip": false,
|
210 |
-
"normalized": false,
|
211 |
-
"special": true
|
212 |
-
},
|
213 |
-
{
|
214 |
-
"id": 30,
|
215 |
-
"content": "<commit_after>",
|
216 |
-
"single_word": false,
|
217 |
-
"lstrip": false,
|
218 |
-
"rstrip": false,
|
219 |
-
"normalized": false,
|
220 |
-
"special": true
|
221 |
-
},
|
222 |
-
{
|
223 |
-
"id": 31,
|
224 |
-
"content": "<reponame>",
|
225 |
-
"single_word": false,
|
226 |
-
"lstrip": false,
|
227 |
-
"rstrip": false,
|
228 |
-
"normalized": false,
|
229 |
-
"special": true
|
230 |
-
},
|
231 |
-
{
|
232 |
-
"id": 32,
|
233 |
-
"content": "<h1>",
|
234 |
-
"single_word": false,
|
235 |
-
"lstrip": false,
|
236 |
-
"rstrip": false,
|
237 |
-
"normalized": false,
|
238 |
-
"special": true
|
239 |
-
},
|
240 |
-
{
|
241 |
-
"id": 33,
|
242 |
-
"content": "<h1/>",
|
243 |
-
"single_word": false,
|
244 |
-
"lstrip": false,
|
245 |
-
"rstrip": false,
|
246 |
-
"normalized": false,
|
247 |
-
"special": true
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"id": 34,
|
251 |
-
"content": "</h1>",
|
252 |
-
"single_word": false,
|
253 |
-
"lstrip": false,
|
254 |
-
"rstrip": false,
|
255 |
-
"normalized": false,
|
256 |
-
"special": true
|
257 |
-
},
|
258 |
-
{
|
259 |
-
"id": 35,
|
260 |
-
"content": "<h2>",
|
261 |
-
"single_word": false,
|
262 |
-
"lstrip": false,
|
263 |
-
"rstrip": false,
|
264 |
-
"normalized": false,
|
265 |
-
"special": true
|
266 |
-
},
|
267 |
-
{
|
268 |
-
"id": 36,
|
269 |
-
"content": "<h2/>",
|
270 |
-
"single_word": false,
|
271 |
-
"lstrip": false,
|
272 |
-
"rstrip": false,
|
273 |
-
"normalized": false,
|
274 |
-
"special": true
|
275 |
-
},
|
276 |
-
{
|
277 |
-
"id": 37,
|
278 |
-
"content": "</h2>",
|
279 |
-
"single_word": false,
|
280 |
-
"lstrip": false,
|
281 |
-
"rstrip": false,
|
282 |
-
"normalized": false,
|
283 |
-
"special": true
|
284 |
-
},
|
285 |
-
{
|
286 |
-
"id": 38,
|
287 |
-
"content": "<h3>",
|
288 |
-
"single_word": false,
|
289 |
-
"lstrip": false,
|
290 |
-
"rstrip": false,
|
291 |
-
"normalized": false,
|
292 |
-
"special": true
|
293 |
-
},
|
294 |
-
{
|
295 |
-
"id": 39,
|
296 |
-
"content": "<h3/>",
|
297 |
-
"single_word": false,
|
298 |
-
"lstrip": false,
|
299 |
-
"rstrip": false,
|
300 |
-
"normalized": false,
|
301 |
-
"special": true
|
302 |
-
},
|
303 |
-
{
|
304 |
-
"id": 40,
|
305 |
-
"content": "</h3>",
|
306 |
-
"single_word": false,
|
307 |
-
"lstrip": false,
|
308 |
-
"rstrip": false,
|
309 |
-
"normalized": false,
|
310 |
-
"special": true
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"id": 41,
|
314 |
-
"content": "<h4>",
|
315 |
-
"single_word": false,
|
316 |
-
"lstrip": false,
|
317 |
-
"rstrip": false,
|
318 |
-
"normalized": false,
|
319 |
-
"special": true
|
320 |
-
},
|
321 |
-
{
|
322 |
-
"id": 42,
|
323 |
-
"content": "<h4/>",
|
324 |
-
"single_word": false,
|
325 |
-
"lstrip": false,
|
326 |
-
"rstrip": false,
|
327 |
-
"normalized": false,
|
328 |
-
"special": true
|
329 |
-
},
|
330 |
-
{
|
331 |
-
"id": 43,
|
332 |
-
"content": "</h4>",
|
333 |
-
"single_word": false,
|
334 |
-
"lstrip": false,
|
335 |
-
"rstrip": false,
|
336 |
-
"normalized": false,
|
337 |
-
"special": true
|
338 |
-
},
|
339 |
-
{
|
340 |
-
"id": 44,
|
341 |
-
"content": "<h5>",
|
342 |
-
"single_word": false,
|
343 |
-
"lstrip": false,
|
344 |
-
"rstrip": false,
|
345 |
-
"normalized": false,
|
346 |
-
"special": true
|
347 |
-
},
|
348 |
-
{
|
349 |
-
"id": 45,
|
350 |
-
"content": "<h5/>",
|
351 |
-
"single_word": false,
|
352 |
-
"lstrip": false,
|
353 |
-
"rstrip": false,
|
354 |
-
"normalized": false,
|
355 |
-
"special": true
|
356 |
-
},
|
357 |
-
{
|
358 |
-
"id": 46,
|
359 |
-
"content": "</h5>",
|
360 |
-
"single_word": false,
|
361 |
-
"lstrip": false,
|
362 |
-
"rstrip": false,
|
363 |
-
"normalized": false,
|
364 |
-
"special": true
|
365 |
-
},
|
366 |
-
{
|
367 |
-
"id": 47,
|
368 |
-
"content": "<br>",
|
369 |
-
"single_word": false,
|
370 |
-
"lstrip": false,
|
371 |
-
"rstrip": false,
|
372 |
-
"normalized": false,
|
373 |
-
"special": true
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"id": 48,
|
377 |
-
"content": "<br/>",
|
378 |
-
"single_word": false,
|
379 |
-
"lstrip": false,
|
380 |
-
"rstrip": false,
|
381 |
-
"normalized": false,
|
382 |
-
"special": true
|
383 |
-
},
|
384 |
-
{
|
385 |
-
"id": 49,
|
386 |
-
"content": "</br>",
|
387 |
-
"single_word": false,
|
388 |
-
"lstrip": false,
|
389 |
-
"rstrip": false,
|
390 |
-
"normalized": false,
|
391 |
-
"special": true
|
392 |
-
},
|
393 |
-
{
|
394 |
-
"id": 50,
|
395 |
-
"content": "<strong>",
|
396 |
-
"single_word": false,
|
397 |
-
"lstrip": false,
|
398 |
-
"rstrip": false,
|
399 |
-
"normalized": false,
|
400 |
-
"special": true
|
401 |
-
},
|
402 |
-
{
|
403 |
-
"id": 51,
|
404 |
-
"content": "<strong/>",
|
405 |
-
"single_word": false,
|
406 |
-
"lstrip": false,
|
407 |
-
"rstrip": false,
|
408 |
-
"normalized": false,
|
409 |
-
"special": true
|
410 |
-
},
|
411 |
-
{
|
412 |
-
"id": 52,
|
413 |
-
"content": "</strong>",
|
414 |
-
"single_word": false,
|
415 |
-
"lstrip": false,
|
416 |
-
"rstrip": false,
|
417 |
-
"normalized": false,
|
418 |
-
"special": true
|
419 |
-
},
|
420 |
-
{
|
421 |
-
"id": 53,
|
422 |
-
"content": "<p>",
|
423 |
-
"single_word": false,
|
424 |
-
"lstrip": false,
|
425 |
-
"rstrip": false,
|
426 |
-
"normalized": false,
|
427 |
-
"special": true
|
428 |
-
},
|
429 |
-
{
|
430 |
-
"id": 54,
|
431 |
-
"content": "<p/>",
|
432 |
-
"single_word": false,
|
433 |
-
"lstrip": false,
|
434 |
-
"rstrip": false,
|
435 |
-
"normalized": false,
|
436 |
-
"special": true
|
437 |
-
},
|
438 |
-
{
|
439 |
-
"id": 55,
|
440 |
-
"content": "</p>",
|
441 |
-
"single_word": false,
|
442 |
-
"lstrip": false,
|
443 |
-
"rstrip": false,
|
444 |
-
"normalized": false,
|
445 |
-
"special": true
|
446 |
-
},
|
447 |
-
{
|
448 |
-
"id": 56,
|
449 |
-
"content": "<table>",
|
450 |
-
"single_word": false,
|
451 |
-
"lstrip": false,
|
452 |
-
"rstrip": false,
|
453 |
-
"normalized": false,
|
454 |
-
"special": true
|
455 |
-
},
|
456 |
-
{
|
457 |
-
"id": 57,
|
458 |
-
"content": "<table/>",
|
459 |
-
"single_word": false,
|
460 |
-
"lstrip": false,
|
461 |
-
"rstrip": false,
|
462 |
-
"normalized": false,
|
463 |
-
"special": true
|
464 |
-
},
|
465 |
-
{
|
466 |
-
"id": 58,
|
467 |
-
"content": "</table>",
|
468 |
-
"single_word": false,
|
469 |
-
"lstrip": false,
|
470 |
-
"rstrip": false,
|
471 |
-
"normalized": false,
|
472 |
-
"special": true
|
473 |
-
},
|
474 |
-
{
|
475 |
-
"id": 59,
|
476 |
-
"content": "<li>",
|
477 |
-
"single_word": false,
|
478 |
-
"lstrip": false,
|
479 |
-
"rstrip": false,
|
480 |
-
"normalized": false,
|
481 |
-
"special": true
|
482 |
-
},
|
483 |
-
{
|
484 |
-
"id": 60,
|
485 |
-
"content": "<li/>",
|
486 |
-
"single_word": false,
|
487 |
-
"lstrip": false,
|
488 |
-
"rstrip": false,
|
489 |
-
"normalized": false,
|
490 |
-
"special": true
|
491 |
-
},
|
492 |
-
{
|
493 |
-
"id": 61,
|
494 |
-
"content": "</li>",
|
495 |
-
"single_word": false,
|
496 |
-
"lstrip": false,
|
497 |
-
"rstrip": false,
|
498 |
-
"normalized": false,
|
499 |
-
"special": true
|
500 |
-
},
|
501 |
-
{
|
502 |
-
"id": 62,
|
503 |
-
"content": "<tr>",
|
504 |
-
"single_word": false,
|
505 |
-
"lstrip": false,
|
506 |
-
"rstrip": false,
|
507 |
-
"normalized": false,
|
508 |
-
"special": true
|
509 |
-
},
|
510 |
-
{
|
511 |
-
"id": 63,
|
512 |
-
"content": "<tr/>",
|
513 |
-
"single_word": false,
|
514 |
-
"lstrip": false,
|
515 |
-
"rstrip": false,
|
516 |
-
"normalized": false,
|
517 |
-
"special": true
|
518 |
-
},
|
519 |
-
{
|
520 |
-
"id": 64,
|
521 |
-
"content": "</tr>",
|
522 |
-
"single_word": false,
|
523 |
-
"lstrip": false,
|
524 |
-
"rstrip": false,
|
525 |
-
"normalized": false,
|
526 |
-
"special": true
|
527 |
-
},
|
528 |
-
{
|
529 |
-
"id": 65,
|
530 |
-
"content": "<tbody>",
|
531 |
-
"single_word": false,
|
532 |
-
"lstrip": false,
|
533 |
-
"rstrip": false,
|
534 |
-
"normalized": false,
|
535 |
-
"special": true
|
536 |
-
},
|
537 |
-
{
|
538 |
-
"id": 66,
|
539 |
-
"content": "<tbody/>",
|
540 |
-
"single_word": false,
|
541 |
-
"lstrip": false,
|
542 |
-
"rstrip": false,
|
543 |
-
"normalized": false,
|
544 |
-
"special": true
|
545 |
-
},
|
546 |
-
{
|
547 |
-
"id": 67,
|
548 |
-
"content": "</tbody>",
|
549 |
-
"single_word": false,
|
550 |
-
"lstrip": false,
|
551 |
-
"rstrip": false,
|
552 |
-
"normalized": false,
|
553 |
-
"special": true
|
554 |
-
},
|
555 |
-
{
|
556 |
-
"id": 68,
|
557 |
-
"content": "<img>",
|
558 |
-
"single_word": false,
|
559 |
-
"lstrip": false,
|
560 |
-
"rstrip": false,
|
561 |
-
"normalized": false,
|
562 |
-
"special": true
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"id": 69,
|
566 |
-
"content": "<img/>",
|
567 |
-
"single_word": false,
|
568 |
-
"lstrip": false,
|
569 |
-
"rstrip": false,
|
570 |
-
"normalized": false,
|
571 |
-
"special": true
|
572 |
-
},
|
573 |
-
{
|
574 |
-
"id": 70,
|
575 |
-
"content": "</img>",
|
576 |
-
"single_word": false,
|
577 |
-
"lstrip": false,
|
578 |
-
"rstrip": false,
|
579 |
-
"normalized": false,
|
580 |
-
"special": true
|
581 |
-
},
|
582 |
-
{
|
583 |
-
"id": 71,
|
584 |
-
"content": "<b>",
|
585 |
-
"single_word": false,
|
586 |
-
"lstrip": false,
|
587 |
-
"rstrip": false,
|
588 |
-
"normalized": false,
|
589 |
-
"special": true
|
590 |
-
},
|
591 |
-
{
|
592 |
-
"id": 72,
|
593 |
-
"content": "<b/>",
|
594 |
-
"single_word": false,
|
595 |
-
"lstrip": false,
|
596 |
-
"rstrip": false,
|
597 |
-
"normalized": false,
|
598 |
-
"special": true
|
599 |
-
},
|
600 |
-
{
|
601 |
-
"id": 73,
|
602 |
-
"content": "</b>",
|
603 |
-
"single_word": false,
|
604 |
-
"lstrip": false,
|
605 |
-
"rstrip": false,
|
606 |
-
"normalized": false,
|
607 |
-
"special": true
|
608 |
-
},
|
609 |
-
{
|
610 |
-
"id": 74,
|
611 |
-
"content": "<td>",
|
612 |
-
"single_word": false,
|
613 |
-
"lstrip": false,
|
614 |
-
"rstrip": false,
|
615 |
-
"normalized": false,
|
616 |
-
"special": true
|
617 |
-
},
|
618 |
-
{
|
619 |
-
"id": 75,
|
620 |
-
"content": "<td/>",
|
621 |
-
"single_word": false,
|
622 |
-
"lstrip": false,
|
623 |
-
"rstrip": false,
|
624 |
-
"normalized": false,
|
625 |
-
"special": true
|
626 |
-
},
|
627 |
-
{
|
628 |
-
"id": 76,
|
629 |
-
"content": "</td>",
|
630 |
-
"single_word": false,
|
631 |
-
"lstrip": false,
|
632 |
-
"rstrip": false,
|
633 |
-
"normalized": false,
|
634 |
-
"special": true
|
635 |
-
},
|
636 |
-
{
|
637 |
-
"id": 115,
|
638 |
-
"content": "<!--",
|
639 |
-
"single_word": false,
|
640 |
-
"lstrip": false,
|
641 |
-
"rstrip": false,
|
642 |
-
"normalized": false,
|
643 |
-
"special": true
|
644 |
-
},
|
645 |
-
{
|
646 |
-
"id": 118,
|
647 |
-
"content": "<!DOCTYPE>",
|
648 |
-
"single_word": false,
|
649 |
-
"lstrip": false,
|
650 |
-
"rstrip": false,
|
651 |
-
"normalized": false,
|
652 |
-
"special": true
|
653 |
-
},
|
654 |
-
{
|
655 |
-
"id": 145,
|
656 |
-
"content": "<|unused000|>",
|
657 |
-
"single_word": false,
|
658 |
-
"lstrip": false,
|
659 |
-
"rstrip": false,
|
660 |
-
"normalized": false,
|
661 |
-
"special": true
|
662 |
-
},
|
663 |
-
{
|
664 |
-
"id": 146,
|
665 |
-
"content": "<|unused001|>",
|
666 |
-
"single_word": false,
|
667 |
-
"lstrip": false,
|
668 |
-
"rstrip": false,
|
669 |
-
"normalized": false,
|
670 |
-
"special": true
|
671 |
-
},
|
672 |
-
{
|
673 |
-
"id": 147,
|
674 |
-
"content": "<|unused002|>",
|
675 |
-
"single_word": false,
|
676 |
-
"lstrip": false,
|
677 |
-
"rstrip": false,
|
678 |
-
"normalized": false,
|
679 |
-
"special": true
|
680 |
-
},
|
681 |
-
{
|
682 |
-
"id": 148,
|
683 |
-
"content": "<|unused003|>",
|
684 |
-
"single_word": false,
|
685 |
-
"lstrip": false,
|
686 |
-
"rstrip": false,
|
687 |
-
"normalized": false,
|
688 |
-
"special": true
|
689 |
-
},
|
690 |
-
{
|
691 |
-
"id": 149,
|
692 |
-
"content": "<|unused004|>",
|
693 |
-
"single_word": false,
|
694 |
-
"lstrip": false,
|
695 |
-
"rstrip": false,
|
696 |
-
"normalized": false,
|
697 |
-
"special": true
|
698 |
-
},
|
699 |
-
{
|
700 |
-
"id": 150,
|
701 |
-
"content": "<|unused005|>",
|
702 |
-
"single_word": false,
|
703 |
-
"lstrip": false,
|
704 |
-
"rstrip": false,
|
705 |
-
"normalized": false,
|
706 |
-
"special": true
|
707 |
-
},
|
708 |
-
{
|
709 |
-
"id": 151,
|
710 |
-
"content": "<|unused006|>",
|
711 |
-
"single_word": false,
|
712 |
-
"lstrip": false,
|
713 |
-
"rstrip": false,
|
714 |
-
"normalized": false,
|
715 |
-
"special": true
|
716 |
-
},
|
717 |
-
{
|
718 |
-
"id": 152,
|
719 |
-
"content": "<|unused007|>",
|
720 |
-
"single_word": false,
|
721 |
-
"lstrip": false,
|
722 |
-
"rstrip": false,
|
723 |
-
"normalized": false,
|
724 |
-
"special": true
|
725 |
-
},
|
726 |
-
{
|
727 |
-
"id": 153,
|
728 |
-
"content": "<|unused008|>",
|
729 |
-
"single_word": false,
|
730 |
-
"lstrip": false,
|
731 |
-
"rstrip": false,
|
732 |
-
"normalized": false,
|
733 |
-
"special": true
|
734 |
-
},
|
735 |
-
{
|
736 |
-
"id": 154,
|
737 |
-
"content": "<|unused009|>",
|
738 |
-
"single_word": false,
|
739 |
-
"lstrip": false,
|
740 |
-
"rstrip": false,
|
741 |
-
"normalized": false,
|
742 |
-
"special": true
|
743 |
-
},
|
744 |
-
{
|
745 |
-
"id": 155,
|
746 |
-
"content": "<|unused010|>",
|
747 |
-
"single_word": false,
|
748 |
-
"lstrip": false,
|
749 |
-
"rstrip": false,
|
750 |
-
"normalized": false,
|
751 |
-
"special": true
|
752 |
-
},
|
753 |
-
{
|
754 |
-
"id": 156,
|
755 |
-
"content": "<|unused011|>",
|
756 |
-
"single_word": false,
|
757 |
-
"lstrip": false,
|
758 |
-
"rstrip": false,
|
759 |
-
"normalized": false,
|
760 |
-
"special": true
|
761 |
-
},
|
762 |
-
{
|
763 |
-
"id": 157,
|
764 |
-
"content": "<|unused012|>",
|
765 |
-
"single_word": false,
|
766 |
-
"lstrip": false,
|
767 |
-
"rstrip": false,
|
768 |
-
"normalized": false,
|
769 |
-
"special": true
|
770 |
-
},
|
771 |
-
{
|
772 |
-
"id": 158,
|
773 |
-
"content": "<|unused013|>",
|
774 |
-
"single_word": false,
|
775 |
-
"lstrip": false,
|
776 |
-
"rstrip": false,
|
777 |
-
"normalized": false,
|
778 |
-
"special": true
|
779 |
-
},
|
780 |
-
{
|
781 |
-
"id": 159,
|
782 |
-
"content": "<|unused014|>",
|
783 |
-
"single_word": false,
|
784 |
-
"lstrip": false,
|
785 |
-
"rstrip": false,
|
786 |
-
"normalized": false,
|
787 |
-
"special": true
|
788 |
-
},
|
789 |
-
{
|
790 |
-
"id": 160,
|
791 |
-
"content": "<|unused015|>",
|
792 |
-
"single_word": false,
|
793 |
-
"lstrip": false,
|
794 |
-
"rstrip": false,
|
795 |
-
"normalized": false,
|
796 |
-
"special": true
|
797 |
-
},
|
798 |
-
{
|
799 |
-
"id": 161,
|
800 |
-
"content": "<|unused016|>",
|
801 |
-
"single_word": false,
|
802 |
-
"lstrip": false,
|
803 |
-
"rstrip": false,
|
804 |
-
"normalized": false,
|
805 |
-
"special": true
|
806 |
-
},
|
807 |
-
{
|
808 |
-
"id": 162,
|
809 |
-
"content": "<|unused017|>",
|
810 |
-
"single_word": false,
|
811 |
-
"lstrip": false,
|
812 |
-
"rstrip": false,
|
813 |
-
"normalized": false,
|
814 |
-
"special": true
|
815 |
-
},
|
816 |
-
{
|
817 |
-
"id": 163,
|
818 |
-
"content": "<|unused018|>",
|
819 |
-
"single_word": false,
|
820 |
-
"lstrip": false,
|
821 |
-
"rstrip": false,
|
822 |
-
"normalized": false,
|
823 |
-
"special": true
|
824 |
-
},
|
825 |
-
{
|
826 |
-
"id": 164,
|
827 |
-
"content": "<|unused019|>",
|
828 |
-
"single_word": false,
|
829 |
-
"lstrip": false,
|
830 |
-
"rstrip": false,
|
831 |
-
"normalized": false,
|
832 |
-
"special": true
|
833 |
-
},
|
834 |
-
{
|
835 |
-
"id": 165,
|
836 |
-
"content": "<|unused020|>",
|
837 |
-
"single_word": false,
|
838 |
-
"lstrip": false,
|
839 |
-
"rstrip": false,
|
840 |
-
"normalized": false,
|
841 |
-
"special": true
|
842 |
-
},
|
843 |
-
{
|
844 |
-
"id": 166,
|
845 |
-
"content": "<|unused021|>",
|
846 |
-
"single_word": false,
|
847 |
-
"lstrip": false,
|
848 |
-
"rstrip": false,
|
849 |
-
"normalized": false,
|
850 |
-
"special": true
|
851 |
-
},
|
852 |
-
{
|
853 |
-
"id": 167,
|
854 |
-
"content": "<|unused022|>",
|
855 |
-
"single_word": false,
|
856 |
-
"lstrip": false,
|
857 |
-
"rstrip": false,
|
858 |
-
"normalized": false,
|
859 |
-
"special": true
|
860 |
-
},
|
861 |
-
{
|
862 |
-
"id": 168,
|
863 |
-
"content": "<|unused023|>",
|
864 |
-
"single_word": false,
|
865 |
-
"lstrip": false,
|
866 |
-
"rstrip": false,
|
867 |
-
"normalized": false,
|
868 |
-
"special": true
|
869 |
-
},
|
870 |
-
{
|
871 |
-
"id": 169,
|
872 |
-
"content": "<|unused024|>",
|
873 |
-
"single_word": false,
|
874 |
-
"lstrip": false,
|
875 |
-
"rstrip": false,
|
876 |
-
"normalized": false,
|
877 |
-
"special": true
|
878 |
-
},
|
879 |
-
{
|
880 |
-
"id": 170,
|
881 |
-
"content": "<|unused025|>",
|
882 |
-
"single_word": false,
|
883 |
-
"lstrip": false,
|
884 |
-
"rstrip": false,
|
885 |
-
"normalized": false,
|
886 |
-
"special": true
|
887 |
-
},
|
888 |
-
{
|
889 |
-
"id": 171,
|
890 |
-
"content": "<|unused026|>",
|
891 |
-
"single_word": false,
|
892 |
-
"lstrip": false,
|
893 |
-
"rstrip": false,
|
894 |
-
"normalized": false,
|
895 |
-
"special": true
|
896 |
-
},
|
897 |
-
{
|
898 |
-
"id": 172,
|
899 |
-
"content": "<|unused027|>",
|
900 |
-
"single_word": false,
|
901 |
-
"lstrip": false,
|
902 |
-
"rstrip": false,
|
903 |
-
"normalized": false,
|
904 |
-
"special": true
|
905 |
-
},
|
906 |
-
{
|
907 |
-
"id": 173,
|
908 |
-
"content": "<|unused028|>",
|
909 |
-
"single_word": false,
|
910 |
-
"lstrip": false,
|
911 |
-
"rstrip": false,
|
912 |
-
"normalized": false,
|
913 |
-
"special": true
|
914 |
-
},
|
915 |
-
{
|
916 |
-
"id": 174,
|
917 |
-
"content": "<|unused029|>",
|
918 |
-
"single_word": false,
|
919 |
-
"lstrip": false,
|
920 |
-
"rstrip": false,
|
921 |
-
"normalized": false,
|
922 |
-
"special": true
|
923 |
-
},
|
924 |
-
{
|
925 |
-
"id": 175,
|
926 |
-
"content": "<|unused030|>",
|
927 |
-
"single_word": false,
|
928 |
-
"lstrip": false,
|
929 |
-
"rstrip": false,
|
930 |
-
"normalized": false,
|
931 |
-
"special": true
|
932 |
-
},
|
933 |
-
{
|
934 |
-
"id": 176,
|
935 |
-
"content": "<|unused031|>",
|
936 |
-
"single_word": false,
|
937 |
-
"lstrip": false,
|
938 |
-
"rstrip": false,
|
939 |
-
"normalized": false,
|
940 |
-
"special": true
|
941 |
-
},
|
942 |
-
{
|
943 |
-
"id": 177,
|
944 |
-
"content": "<|unused032|>",
|
945 |
-
"single_word": false,
|
946 |
-
"lstrip": false,
|
947 |
-
"rstrip": false,
|
948 |
-
"normalized": false,
|
949 |
-
"special": true
|
950 |
-
},
|
951 |
-
{
|
952 |
-
"id": 178,
|
953 |
-
"content": "<|unused033|>",
|
954 |
-
"single_word": false,
|
955 |
-
"lstrip": false,
|
956 |
-
"rstrip": false,
|
957 |
-
"normalized": false,
|
958 |
-
"special": true
|
959 |
-
},
|
960 |
-
{
|
961 |
-
"id": 179,
|
962 |
-
"content": "<|unused034|>",
|
963 |
-
"single_word": false,
|
964 |
-
"lstrip": false,
|
965 |
-
"rstrip": false,
|
966 |
-
"normalized": false,
|
967 |
-
"special": true
|
968 |
-
},
|
969 |
-
{
|
970 |
-
"id": 180,
|
971 |
-
"content": "<|unused035|>",
|
972 |
-
"single_word": false,
|
973 |
-
"lstrip": false,
|
974 |
-
"rstrip": false,
|
975 |
-
"normalized": false,
|
976 |
-
"special": true
|
977 |
-
},
|
978 |
-
{
|
979 |
-
"id": 181,
|
980 |
-
"content": "<|unused036|>",
|
981 |
-
"single_word": false,
|
982 |
-
"lstrip": false,
|
983 |
-
"rstrip": false,
|
984 |
-
"normalized": false,
|
985 |
-
"special": true
|
986 |
-
},
|
987 |
-
{
|
988 |
-
"id": 182,
|
989 |
-
"content": "<|unused037|>",
|
990 |
-
"single_word": false,
|
991 |
-
"lstrip": false,
|
992 |
-
"rstrip": false,
|
993 |
-
"normalized": false,
|
994 |
-
"special": true
|
995 |
-
},
|
996 |
-
{
|
997 |
-
"id": 183,
|
998 |
-
"content": "<|unused038|>",
|
999 |
-
"single_word": false,
|
1000 |
-
"lstrip": false,
|
1001 |
-
"rstrip": false,
|
1002 |
-
"normalized": false,
|
1003 |
-
"special": true
|
1004 |
-
},
|
1005 |
-
{
|
1006 |
-
"id": 184,
|
1007 |
-
"content": "<|unused039|>",
|
1008 |
-
"single_word": false,
|
1009 |
-
"lstrip": false,
|
1010 |
-
"rstrip": false,
|
1011 |
-
"normalized": false,
|
1012 |
-
"special": true
|
1013 |
-
},
|
1014 |
-
{
|
1015 |
-
"id": 185,
|
1016 |
-
"content": "<|unused040|>",
|
1017 |
-
"single_word": false,
|
1018 |
-
"lstrip": false,
|
1019 |
-
"rstrip": false,
|
1020 |
-
"normalized": false,
|
1021 |
-
"special": true
|
1022 |
-
},
|
1023 |
-
{
|
1024 |
-
"id": 186,
|
1025 |
-
"content": "<|unused041|>",
|
1026 |
-
"single_word": false,
|
1027 |
-
"lstrip": false,
|
1028 |
-
"rstrip": false,
|
1029 |
-
"normalized": false,
|
1030 |
-
"special": true
|
1031 |
-
},
|
1032 |
-
{
|
1033 |
-
"id": 187,
|
1034 |
-
"content": "<|unused042|>",
|
1035 |
-
"single_word": false,
|
1036 |
-
"lstrip": false,
|
1037 |
-
"rstrip": false,
|
1038 |
-
"normalized": false,
|
1039 |
-
"special": true
|
1040 |
-
},
|
1041 |
-
{
|
1042 |
-
"id": 188,
|
1043 |
-
"content": "<|unused043|>",
|
1044 |
-
"single_word": false,
|
1045 |
-
"lstrip": false,
|
1046 |
-
"rstrip": false,
|
1047 |
-
"normalized": false,
|
1048 |
-
"special": true
|
1049 |
-
},
|
1050 |
-
{
|
1051 |
-
"id": 189,
|
1052 |
-
"content": "<|unused044|>",
|
1053 |
-
"single_word": false,
|
1054 |
-
"lstrip": false,
|
1055 |
-
"rstrip": false,
|
1056 |
-
"normalized": false,
|
1057 |
-
"special": true
|
1058 |
-
},
|
1059 |
-
{
|
1060 |
-
"id": 190,
|
1061 |
-
"content": "<|unused045|>",
|
1062 |
-
"single_word": false,
|
1063 |
-
"lstrip": false,
|
1064 |
-
"rstrip": false,
|
1065 |
-
"normalized": false,
|
1066 |
-
"special": true
|
1067 |
-
},
|
1068 |
-
{
|
1069 |
-
"id": 191,
|
1070 |
-
"content": "<|unused046|>",
|
1071 |
-
"single_word": false,
|
1072 |
-
"lstrip": false,
|
1073 |
-
"rstrip": false,
|
1074 |
-
"normalized": false,
|
1075 |
-
"special": true
|
1076 |
-
},
|
1077 |
-
{
|
1078 |
-
"id": 192,
|
1079 |
-
"content": "<|unused047|>",
|
1080 |
-
"single_word": false,
|
1081 |
-
"lstrip": false,
|
1082 |
-
"rstrip": false,
|
1083 |
-
"normalized": false,
|
1084 |
-
"special": true
|
1085 |
-
},
|
1086 |
-
{
|
1087 |
-
"id": 193,
|
1088 |
-
"content": "<|unused048|>",
|
1089 |
-
"single_word": false,
|
1090 |
-
"lstrip": false,
|
1091 |
-
"rstrip": false,
|
1092 |
-
"normalized": false,
|
1093 |
-
"special": true
|
1094 |
-
},
|
1095 |
-
{
|
1096 |
-
"id": 194,
|
1097 |
-
"content": "<|unused049|>",
|
1098 |
-
"single_word": false,
|
1099 |
-
"lstrip": false,
|
1100 |
-
"rstrip": false,
|
1101 |
-
"normalized": false,
|
1102 |
-
"special": true
|
1103 |
-
},
|
1104 |
-
{
|
1105 |
-
"id": 195,
|
1106 |
-
"content": "<|unused050|>",
|
1107 |
-
"single_word": false,
|
1108 |
-
"lstrip": false,
|
1109 |
-
"rstrip": false,
|
1110 |
-
"normalized": false,
|
1111 |
-
"special": true
|
1112 |
-
},
|
1113 |
-
{
|
1114 |
-
"id": 196,
|
1115 |
-
"content": "<|unused051|>",
|
1116 |
-
"single_word": false,
|
1117 |
-
"lstrip": false,
|
1118 |
-
"rstrip": false,
|
1119 |
-
"normalized": false,
|
1120 |
-
"special": true
|
1121 |
-
},
|
1122 |
-
{
|
1123 |
-
"id": 197,
|
1124 |
-
"content": "<|unused052|>",
|
1125 |
-
"single_word": false,
|
1126 |
-
"lstrip": false,
|
1127 |
-
"rstrip": false,
|
1128 |
-
"normalized": false,
|
1129 |
-
"special": true
|
1130 |
-
},
|
1131 |
-
{
|
1132 |
-
"id": 198,
|
1133 |
-
"content": "<|unused053|>",
|
1134 |
-
"single_word": false,
|
1135 |
-
"lstrip": false,
|
1136 |
-
"rstrip": false,
|
1137 |
-
"normalized": false,
|
1138 |
-
"special": true
|
1139 |
-
},
|
1140 |
-
{
|
1141 |
-
"id": 199,
|
1142 |
-
"content": "<|unused054|>",
|
1143 |
-
"single_word": false,
|
1144 |
-
"lstrip": false,
|
1145 |
-
"rstrip": false,
|
1146 |
-
"normalized": false,
|
1147 |
-
"special": true
|
1148 |
-
},
|
1149 |
-
{
|
1150 |
-
"id": 200,
|
1151 |
-
"content": "<|unused055|>",
|
1152 |
-
"single_word": false,
|
1153 |
-
"lstrip": false,
|
1154 |
-
"rstrip": false,
|
1155 |
-
"normalized": false,
|
1156 |
-
"special": true
|
1157 |
-
},
|
1158 |
-
{
|
1159 |
-
"id": 201,
|
1160 |
-
"content": "<|unused056|>",
|
1161 |
-
"single_word": false,
|
1162 |
-
"lstrip": false,
|
1163 |
-
"rstrip": false,
|
1164 |
-
"normalized": false,
|
1165 |
-
"special": true
|
1166 |
-
},
|
1167 |
-
{
|
1168 |
-
"id": 202,
|
1169 |
-
"content": "<|unused057|>",
|
1170 |
-
"single_word": false,
|
1171 |
-
"lstrip": false,
|
1172 |
-
"rstrip": false,
|
1173 |
-
"normalized": false,
|
1174 |
-
"special": true
|
1175 |
-
},
|
1176 |
-
{
|
1177 |
-
"id": 203,
|
1178 |
-
"content": "<|unused058|>",
|
1179 |
-
"single_word": false,
|
1180 |
-
"lstrip": false,
|
1181 |
-
"rstrip": false,
|
1182 |
-
"normalized": false,
|
1183 |
-
"special": true
|
1184 |
-
},
|
1185 |
-
{
|
1186 |
-
"id": 204,
|
1187 |
-
"content": "<|unused059|>",
|
1188 |
-
"single_word": false,
|
1189 |
-
"lstrip": false,
|
1190 |
-
"rstrip": false,
|
1191 |
-
"normalized": false,
|
1192 |
-
"special": true
|
1193 |
-
},
|
1194 |
-
{
|
1195 |
-
"id": 205,
|
1196 |
-
"content": "<|unused060|>",
|
1197 |
-
"single_word": false,
|
1198 |
-
"lstrip": false,
|
1199 |
-
"rstrip": false,
|
1200 |
-
"normalized": false,
|
1201 |
-
"special": true
|
1202 |
-
},
|
1203 |
-
{
|
1204 |
-
"id": 206,
|
1205 |
-
"content": "<|unused061|>",
|
1206 |
-
"single_word": false,
|
1207 |
-
"lstrip": false,
|
1208 |
-
"rstrip": false,
|
1209 |
-
"normalized": false,
|
1210 |
-
"special": true
|
1211 |
-
},
|
1212 |
-
{
|
1213 |
-
"id": 207,
|
1214 |
-
"content": "<|unused062|>",
|
1215 |
-
"single_word": false,
|
1216 |
-
"lstrip": false,
|
1217 |
-
"rstrip": false,
|
1218 |
-
"normalized": false,
|
1219 |
-
"special": true
|
1220 |
-
},
|
1221 |
-
{
|
1222 |
-
"id": 208,
|
1223 |
-
"content": "<|unused063|>",
|
1224 |
-
"single_word": false,
|
1225 |
-
"lstrip": false,
|
1226 |
-
"rstrip": false,
|
1227 |
-
"normalized": false,
|
1228 |
-
"special": true
|
1229 |
-
},
|
1230 |
-
{
|
1231 |
-
"id": 209,
|
1232 |
-
"content": "<|unused064|>",
|
1233 |
-
"single_word": false,
|
1234 |
-
"lstrip": false,
|
1235 |
-
"rstrip": false,
|
1236 |
-
"normalized": false,
|
1237 |
-
"special": true
|
1238 |
-
},
|
1239 |
-
{
|
1240 |
-
"id": 210,
|
1241 |
-
"content": "<|unused065|>",
|
1242 |
-
"single_word": false,
|
1243 |
-
"lstrip": false,
|
1244 |
-
"rstrip": false,
|
1245 |
-
"normalized": false,
|
1246 |
-
"special": true
|
1247 |
-
},
|
1248 |
-
{
|
1249 |
-
"id": 211,
|
1250 |
-
"content": "<|unused066|>",
|
1251 |
-
"single_word": false,
|
1252 |
-
"lstrip": false,
|
1253 |
-
"rstrip": false,
|
1254 |
-
"normalized": false,
|
1255 |
-
"special": true
|
1256 |
-
},
|
1257 |
-
{
|
1258 |
-
"id": 212,
|
1259 |
-
"content": "<|unused067|>",
|
1260 |
-
"single_word": false,
|
1261 |
-
"lstrip": false,
|
1262 |
-
"rstrip": false,
|
1263 |
-
"normalized": false,
|
1264 |
-
"special": true
|
1265 |
-
},
|
1266 |
-
{
|
1267 |
-
"id": 213,
|
1268 |
-
"content": "<|unused068|>",
|
1269 |
-
"single_word": false,
|
1270 |
-
"lstrip": false,
|
1271 |
-
"rstrip": false,
|
1272 |
-
"normalized": false,
|
1273 |
-
"special": true
|
1274 |
-
},
|
1275 |
-
{
|
1276 |
-
"id": 214,
|
1277 |
-
"content": "<|unused069|>",
|
1278 |
-
"single_word": false,
|
1279 |
-
"lstrip": false,
|
1280 |
-
"rstrip": false,
|
1281 |
-
"normalized": false,
|
1282 |
-
"special": true
|
1283 |
-
},
|
1284 |
-
{
|
1285 |
-
"id": 215,
|
1286 |
-
"content": "<|unused070|>",
|
1287 |
-
"single_word": false,
|
1288 |
-
"lstrip": false,
|
1289 |
-
"rstrip": false,
|
1290 |
-
"normalized": false,
|
1291 |
-
"special": true
|
1292 |
-
},
|
1293 |
-
{
|
1294 |
-
"id": 216,
|
1295 |
-
"content": "<|unused071|>",
|
1296 |
-
"single_word": false,
|
1297 |
-
"lstrip": false,
|
1298 |
-
"rstrip": false,
|
1299 |
-
"normalized": false,
|
1300 |
-
"special": true
|
1301 |
-
},
|
1302 |
-
{
|
1303 |
-
"id": 217,
|
1304 |
-
"content": "<|unused072|>",
|
1305 |
-
"single_word": false,
|
1306 |
-
"lstrip": false,
|
1307 |
-
"rstrip": false,
|
1308 |
-
"normalized": false,
|
1309 |
-
"special": true
|
1310 |
-
},
|
1311 |
-
{
|
1312 |
-
"id": 218,
|
1313 |
-
"content": "<|unused073|>",
|
1314 |
-
"single_word": false,
|
1315 |
-
"lstrip": false,
|
1316 |
-
"rstrip": false,
|
1317 |
-
"normalized": false,
|
1318 |
-
"special": true
|
1319 |
-
},
|
1320 |
-
{
|
1321 |
-
"id": 219,
|
1322 |
-
"content": "<|unused074|>",
|
1323 |
-
"single_word": false,
|
1324 |
-
"lstrip": false,
|
1325 |
-
"rstrip": false,
|
1326 |
-
"normalized": false,
|
1327 |
-
"special": true
|
1328 |
-
},
|
1329 |
-
{
|
1330 |
-
"id": 220,
|
1331 |
-
"content": "<|unused075|>",
|
1332 |
-
"single_word": false,
|
1333 |
-
"lstrip": false,
|
1334 |
-
"rstrip": false,
|
1335 |
-
"normalized": false,
|
1336 |
-
"special": true
|
1337 |
-
},
|
1338 |
-
{
|
1339 |
-
"id": 221,
|
1340 |
-
"content": "<|unused076|>",
|
1341 |
-
"single_word": false,
|
1342 |
-
"lstrip": false,
|
1343 |
-
"rstrip": false,
|
1344 |
-
"normalized": false,
|
1345 |
-
"special": true
|
1346 |
-
},
|
1347 |
-
{
|
1348 |
-
"id": 222,
|
1349 |
-
"content": "<|unused077|>",
|
1350 |
-
"single_word": false,
|
1351 |
-
"lstrip": false,
|
1352 |
-
"rstrip": false,
|
1353 |
-
"normalized": false,
|
1354 |
-
"special": true
|
1355 |
-
},
|
1356 |
-
{
|
1357 |
-
"id": 223,
|
1358 |
-
"content": "<|unused078|>",
|
1359 |
-
"single_word": false,
|
1360 |
-
"lstrip": false,
|
1361 |
-
"rstrip": false,
|
1362 |
-
"normalized": false,
|
1363 |
-
"special": true
|
1364 |
-
},
|
1365 |
-
{
|
1366 |
-
"id": 224,
|
1367 |
-
"content": "<|unused079|>",
|
1368 |
-
"single_word": false,
|
1369 |
-
"lstrip": false,
|
1370 |
-
"rstrip": false,
|
1371 |
-
"normalized": false,
|
1372 |
-
"special": true
|
1373 |
-
},
|
1374 |
-
{
|
1375 |
-
"id": 225,
|
1376 |
-
"content": "<|unused080|>",
|
1377 |
-
"single_word": false,
|
1378 |
-
"lstrip": false,
|
1379 |
-
"rstrip": false,
|
1380 |
-
"normalized": false,
|
1381 |
-
"special": true
|
1382 |
-
},
|
1383 |
-
{
|
1384 |
-
"id": 226,
|
1385 |
-
"content": "<|unused081|>",
|
1386 |
-
"single_word": false,
|
1387 |
-
"lstrip": false,
|
1388 |
-
"rstrip": false,
|
1389 |
-
"normalized": false,
|
1390 |
-
"special": true
|
1391 |
-
},
|
1392 |
-
{
|
1393 |
-
"id": 227,
|
1394 |
-
"content": "<|unused082|>",
|
1395 |
-
"single_word": false,
|
1396 |
-
"lstrip": false,
|
1397 |
-
"rstrip": false,
|
1398 |
-
"normalized": false,
|
1399 |
-
"special": true
|
1400 |
-
},
|
1401 |
-
{
|
1402 |
-
"id": 228,
|
1403 |
-
"content": "<|unused083|>",
|
1404 |
-
"single_word": false,
|
1405 |
-
"lstrip": false,
|
1406 |
-
"rstrip": false,
|
1407 |
-
"normalized": false,
|
1408 |
-
"special": true
|
1409 |
-
},
|
1410 |
-
{
|
1411 |
-
"id": 229,
|
1412 |
-
"content": "<|unused084|>",
|
1413 |
-
"single_word": false,
|
1414 |
-
"lstrip": false,
|
1415 |
-
"rstrip": false,
|
1416 |
-
"normalized": false,
|
1417 |
-
"special": true
|
1418 |
-
},
|
1419 |
-
{
|
1420 |
-
"id": 230,
|
1421 |
-
"content": "<|unused085|>",
|
1422 |
-
"single_word": false,
|
1423 |
-
"lstrip": false,
|
1424 |
-
"rstrip": false,
|
1425 |
-
"normalized": false,
|
1426 |
-
"special": true
|
1427 |
-
},
|
1428 |
-
{
|
1429 |
-
"id": 231,
|
1430 |
-
"content": "<|unused086|>",
|
1431 |
-
"single_word": false,
|
1432 |
-
"lstrip": false,
|
1433 |
-
"rstrip": false,
|
1434 |
-
"normalized": false,
|
1435 |
-
"special": true
|
1436 |
-
},
|
1437 |
-
{
|
1438 |
-
"id": 232,
|
1439 |
-
"content": "<|unused087|>",
|
1440 |
-
"single_word": false,
|
1441 |
-
"lstrip": false,
|
1442 |
-
"rstrip": false,
|
1443 |
-
"normalized": false,
|
1444 |
-
"special": true
|
1445 |
-
},
|
1446 |
-
{
|
1447 |
-
"id": 233,
|
1448 |
-
"content": "<|unused088|>",
|
1449 |
-
"single_word": false,
|
1450 |
-
"lstrip": false,
|
1451 |
-
"rstrip": false,
|
1452 |
-
"normalized": false,
|
1453 |
-
"special": true
|
1454 |
-
},
|
1455 |
-
{
|
1456 |
-
"id": 234,
|
1457 |
-
"content": "<|unused089|>",
|
1458 |
-
"single_word": false,
|
1459 |
-
"lstrip": false,
|
1460 |
-
"rstrip": false,
|
1461 |
-
"normalized": false,
|
1462 |
-
"special": true
|
1463 |
-
},
|
1464 |
-
{
|
1465 |
-
"id": 235,
|
1466 |
-
"content": "<|unused090|>",
|
1467 |
-
"single_word": false,
|
1468 |
-
"lstrip": false,
|
1469 |
-
"rstrip": false,
|
1470 |
-
"normalized": false,
|
1471 |
-
"special": true
|
1472 |
-
},
|
1473 |
-
{
|
1474 |
-
"id": 236,
|
1475 |
-
"content": "<|unused091|>",
|
1476 |
-
"single_word": false,
|
1477 |
-
"lstrip": false,
|
1478 |
-
"rstrip": false,
|
1479 |
-
"normalized": false,
|
1480 |
-
"special": true
|
1481 |
-
},
|
1482 |
-
{
|
1483 |
-
"id": 237,
|
1484 |
-
"content": "<|unused092|>",
|
1485 |
-
"single_word": false,
|
1486 |
-
"lstrip": false,
|
1487 |
-
"rstrip": false,
|
1488 |
-
"normalized": false,
|
1489 |
-
"special": true
|
1490 |
-
},
|
1491 |
-
{
|
1492 |
-
"id": 238,
|
1493 |
-
"content": "<|unused093|>",
|
1494 |
-
"single_word": false,
|
1495 |
-
"lstrip": false,
|
1496 |
-
"rstrip": false,
|
1497 |
-
"normalized": false,
|
1498 |
-
"special": true
|
1499 |
-
},
|
1500 |
-
{
|
1501 |
-
"id": 239,
|
1502 |
-
"content": "<|unused094|>",
|
1503 |
-
"single_word": false,
|
1504 |
-
"lstrip": false,
|
1505 |
-
"rstrip": false,
|
1506 |
-
"normalized": false,
|
1507 |
-
"special": true
|
1508 |
-
},
|
1509 |
-
{
|
1510 |
-
"id": 240,
|
1511 |
-
"content": "<|unused095|>",
|
1512 |
-
"single_word": false,
|
1513 |
-
"lstrip": false,
|
1514 |
-
"rstrip": false,
|
1515 |
-
"normalized": false,
|
1516 |
-
"special": true
|
1517 |
-
},
|
1518 |
-
{
|
1519 |
-
"id": 241,
|
1520 |
-
"content": "<|unused096|>",
|
1521 |
-
"single_word": false,
|
1522 |
-
"lstrip": false,
|
1523 |
-
"rstrip": false,
|
1524 |
-
"normalized": false,
|
1525 |
-
"special": true
|
1526 |
-
},
|
1527 |
-
{
|
1528 |
-
"id": 242,
|
1529 |
-
"content": "<|unused097|>",
|
1530 |
-
"single_word": false,
|
1531 |
-
"lstrip": false,
|
1532 |
-
"rstrip": false,
|
1533 |
-
"normalized": false,
|
1534 |
-
"special": true
|
1535 |
-
},
|
1536 |
-
{
|
1537 |
-
"id": 243,
|
1538 |
-
"content": "<|unused098|>",
|
1539 |
-
"single_word": false,
|
1540 |
-
"lstrip": false,
|
1541 |
-
"rstrip": false,
|
1542 |
-
"normalized": false,
|
1543 |
-
"special": true
|
1544 |
-
},
|
1545 |
-
{
|
1546 |
-
"id": 244,
|
1547 |
-
"content": "<|unused099|>",
|
1548 |
-
"single_word": false,
|
1549 |
-
"lstrip": false,
|
1550 |
-
"rstrip": false,
|
1551 |
-
"normalized": false,
|
1552 |
-
"special": true
|
1553 |
-
},
|
1554 |
-
{
|
1555 |
-
"id": 245,
|
1556 |
-
"content": "<|unused100|>",
|
1557 |
-
"single_word": false,
|
1558 |
-
"lstrip": false,
|
1559 |
-
"rstrip": false,
|
1560 |
-
"normalized": false,
|
1561 |
-
"special": true
|
1562 |
-
},
|
1563 |
-
{
|
1564 |
-
"id": 246,
|
1565 |
-
"content": "<|unused101|>",
|
1566 |
-
"single_word": false,
|
1567 |
-
"lstrip": false,
|
1568 |
-
"rstrip": false,
|
1569 |
-
"normalized": false,
|
1570 |
-
"special": true
|
1571 |
-
},
|
1572 |
-
{
|
1573 |
-
"id": 247,
|
1574 |
-
"content": "<|unused102|>",
|
1575 |
-
"single_word": false,
|
1576 |
-
"lstrip": false,
|
1577 |
-
"rstrip": false,
|
1578 |
-
"normalized": false,
|
1579 |
-
"special": true
|
1580 |
-
},
|
1581 |
-
{
|
1582 |
-
"id": 248,
|
1583 |
-
"content": "<|unused103|>",
|
1584 |
-
"single_word": false,
|
1585 |
-
"lstrip": false,
|
1586 |
-
"rstrip": false,
|
1587 |
-
"normalized": false,
|
1588 |
-
"special": true
|
1589 |
-
},
|
1590 |
-
{
|
1591 |
-
"id": 249,
|
1592 |
-
"content": "<|unused104|>",
|
1593 |
-
"single_word": false,
|
1594 |
-
"lstrip": false,
|
1595 |
-
"rstrip": false,
|
1596 |
-
"normalized": false,
|
1597 |
-
"special": true
|
1598 |
-
},
|
1599 |
-
{
|
1600 |
-
"id": 250,
|
1601 |
-
"content": "<|unused105|>",
|
1602 |
-
"single_word": false,
|
1603 |
-
"lstrip": false,
|
1604 |
-
"rstrip": false,
|
1605 |
-
"normalized": false,
|
1606 |
-
"special": true
|
1607 |
-
},
|
1608 |
-
{
|
1609 |
-
"id": 251,
|
1610 |
-
"content": "<|unused106|>",
|
1611 |
-
"single_word": false,
|
1612 |
-
"lstrip": false,
|
1613 |
-
"rstrip": false,
|
1614 |
-
"normalized": false,
|
1615 |
-
"special": true
|
1616 |
-
},
|
1617 |
-
{
|
1618 |
-
"id": 252,
|
1619 |
-
"content": "<|unused107|>",
|
1620 |
-
"single_word": false,
|
1621 |
-
"lstrip": false,
|
1622 |
-
"rstrip": false,
|
1623 |
-
"normalized": false,
|
1624 |
-
"special": true
|
1625 |
-
},
|
1626 |
-
{
|
1627 |
-
"id": 253,
|
1628 |
-
"content": "<|unused108|>",
|
1629 |
-
"single_word": false,
|
1630 |
-
"lstrip": false,
|
1631 |
-
"rstrip": false,
|
1632 |
-
"normalized": false,
|
1633 |
-
"special": true
|
1634 |
-
},
|
1635 |
-
{
|
1636 |
-
"id": 254,
|
1637 |
-
"content": "<|unused109|>",
|
1638 |
-
"single_word": false,
|
1639 |
-
"lstrip": false,
|
1640 |
-
"rstrip": false,
|
1641 |
-
"normalized": false,
|
1642 |
-
"special": true
|
1643 |
-
},
|
1644 |
-
{
|
1645 |
-
"id": 255,
|
1646 |
-
"content": "<|unused110|>",
|
1647 |
-
"single_word": false,
|
1648 |
-
"lstrip": false,
|
1649 |
-
"rstrip": false,
|
1650 |
-
"normalized": false,
|
1651 |
-
"special": true
|
1652 |
-
},
|
1653 |
-
{
|
1654 |
-
"id": 256,
|
1655 |
-
"content": "<|unused111|>",
|
1656 |
-
"single_word": false,
|
1657 |
-
"lstrip": false,
|
1658 |
-
"rstrip": false,
|
1659 |
-
"normalized": false,
|
1660 |
-
"special": true
|
1661 |
-
},
|
1662 |
-
{
|
1663 |
-
"id": 257,
|
1664 |
-
"content": "<|unused112|>",
|
1665 |
-
"single_word": false,
|
1666 |
-
"lstrip": false,
|
1667 |
-
"rstrip": false,
|
1668 |
-
"normalized": false,
|
1669 |
-
"special": true
|
1670 |
-
},
|
1671 |
-
{
|
1672 |
-
"id": 258,
|
1673 |
-
"content": "<|unused113|>",
|
1674 |
-
"single_word": false,
|
1675 |
-
"lstrip": false,
|
1676 |
-
"rstrip": false,
|
1677 |
-
"normalized": false,
|
1678 |
-
"special": true
|
1679 |
-
},
|
1680 |
-
{
|
1681 |
-
"id": 259,
|
1682 |
-
"content": "<|unused114|>",
|
1683 |
-
"single_word": false,
|
1684 |
-
"lstrip": false,
|
1685 |
-
"rstrip": false,
|
1686 |
-
"normalized": false,
|
1687 |
-
"special": true
|
1688 |
-
},
|
1689 |
-
{
|
1690 |
-
"id": 260,
|
1691 |
-
"content": "<|unused115|>",
|
1692 |
-
"single_word": false,
|
1693 |
-
"lstrip": false,
|
1694 |
-
"rstrip": false,
|
1695 |
-
"normalized": false,
|
1696 |
-
"special": true
|
1697 |
-
},
|
1698 |
-
{
|
1699 |
-
"id": 261,
|
1700 |
-
"content": "<|unused116|>",
|
1701 |
-
"single_word": false,
|
1702 |
-
"lstrip": false,
|
1703 |
-
"rstrip": false,
|
1704 |
-
"normalized": false,
|
1705 |
-
"special": true
|
1706 |
-
},
|
1707 |
-
{
|
1708 |
-
"id": 262,
|
1709 |
-
"content": "<|unused117|>",
|
1710 |
-
"single_word": false,
|
1711 |
-
"lstrip": false,
|
1712 |
-
"rstrip": false,
|
1713 |
-
"normalized": false,
|
1714 |
-
"special": true
|
1715 |
-
},
|
1716 |
-
{
|
1717 |
-
"id": 263,
|
1718 |
-
"content": "<|unused118|>",
|
1719 |
-
"single_word": false,
|
1720 |
-
"lstrip": false,
|
1721 |
-
"rstrip": false,
|
1722 |
-
"normalized": false,
|
1723 |
-
"special": true
|
1724 |
-
},
|
1725 |
-
{
|
1726 |
-
"id": 264,
|
1727 |
-
"content": "<|unused119|>",
|
1728 |
-
"single_word": false,
|
1729 |
-
"lstrip": false,
|
1730 |
-
"rstrip": false,
|
1731 |
-
"normalized": false,
|
1732 |
-
"special": true
|
1733 |
-
},
|
1734 |
-
{
|
1735 |
-
"id": 265,
|
1736 |
-
"content": "<|unused120|>",
|
1737 |
-
"single_word": false,
|
1738 |
-
"lstrip": false,
|
1739 |
-
"rstrip": false,
|
1740 |
-
"normalized": false,
|
1741 |
-
"special": true
|
1742 |
-
},
|
1743 |
-
{
|
1744 |
-
"id": 266,
|
1745 |
-
"content": "<|unused121|>",
|
1746 |
-
"single_word": false,
|
1747 |
-
"lstrip": false,
|
1748 |
-
"rstrip": false,
|
1749 |
-
"normalized": false,
|
1750 |
-
"special": true
|
1751 |
-
},
|
1752 |
-
{
|
1753 |
-
"id": 267,
|
1754 |
-
"content": "<|unused122|>",
|
1755 |
-
"single_word": false,
|
1756 |
-
"lstrip": false,
|
1757 |
-
"rstrip": false,
|
1758 |
-
"normalized": false,
|
1759 |
-
"special": true
|
1760 |
-
},
|
1761 |
-
{
|
1762 |
-
"id": 268,
|
1763 |
-
"content": "<|unused123|>",
|
1764 |
-
"single_word": false,
|
1765 |
-
"lstrip": false,
|
1766 |
-
"rstrip": false,
|
1767 |
-
"normalized": false,
|
1768 |
-
"special": true
|
1769 |
-
},
|
1770 |
-
{
|
1771 |
-
"id": 269,
|
1772 |
-
"content": "<|unused124|>",
|
1773 |
-
"single_word": false,
|
1774 |
-
"lstrip": false,
|
1775 |
-
"rstrip": false,
|
1776 |
-
"normalized": false,
|
1777 |
-
"special": true
|
1778 |
-
},
|
1779 |
-
{
|
1780 |
-
"id": 270,
|
1781 |
-
"content": "<|unused125|>",
|
1782 |
-
"single_word": false,
|
1783 |
-
"lstrip": false,
|
1784 |
-
"rstrip": false,
|
1785 |
-
"normalized": false,
|
1786 |
-
"special": true
|
1787 |
-
},
|
1788 |
-
{
|
1789 |
-
"id": 271,
|
1790 |
-
"content": "<|unused126|>",
|
1791 |
-
"single_word": false,
|
1792 |
-
"lstrip": false,
|
1793 |
-
"rstrip": false,
|
1794 |
-
"normalized": false,
|
1795 |
-
"special": true
|
1796 |
-
},
|
1797 |
-
{
|
1798 |
-
"id": 272,
|
1799 |
-
"content": "<|unused127|>",
|
1800 |
-
"single_word": false,
|
1801 |
-
"lstrip": false,
|
1802 |
-
"rstrip": false,
|
1803 |
-
"normalized": false,
|
1804 |
-
"special": true
|
1805 |
-
},
|
1806 |
-
{
|
1807 |
-
"id": 273,
|
1808 |
-
"content": "<|unused128|>",
|
1809 |
-
"single_word": false,
|
1810 |
-
"lstrip": false,
|
1811 |
-
"rstrip": false,
|
1812 |
-
"normalized": false,
|
1813 |
-
"special": true
|
1814 |
-
},
|
1815 |
-
{
|
1816 |
-
"id": 274,
|
1817 |
-
"content": "<|unused129|>",
|
1818 |
-
"single_word": false,
|
1819 |
-
"lstrip": false,
|
1820 |
-
"rstrip": false,
|
1821 |
-
"normalized": false,
|
1822 |
-
"special": true
|
1823 |
-
},
|
1824 |
-
{
|
1825 |
-
"id": 275,
|
1826 |
-
"content": "<|unused130|>",
|
1827 |
-
"single_word": false,
|
1828 |
-
"lstrip": false,
|
1829 |
-
"rstrip": false,
|
1830 |
-
"normalized": false,
|
1831 |
-
"special": true
|
1832 |
-
},
|
1833 |
-
{
|
1834 |
-
"id": 276,
|
1835 |
-
"content": "<|unused131|>",
|
1836 |
-
"single_word": false,
|
1837 |
-
"lstrip": false,
|
1838 |
-
"rstrip": false,
|
1839 |
-
"normalized": false,
|
1840 |
-
"special": true
|
1841 |
-
},
|
1842 |
-
{
|
1843 |
-
"id": 277,
|
1844 |
-
"content": "<|unused132|>",
|
1845 |
-
"single_word": false,
|
1846 |
-
"lstrip": false,
|
1847 |
-
"rstrip": false,
|
1848 |
-
"normalized": false,
|
1849 |
-
"special": true
|
1850 |
-
},
|
1851 |
-
{
|
1852 |
-
"id": 278,
|
1853 |
-
"content": "<|unused133|>",
|
1854 |
-
"single_word": false,
|
1855 |
-
"lstrip": false,
|
1856 |
-
"rstrip": false,
|
1857 |
-
"normalized": false,
|
1858 |
-
"special": true
|
1859 |
-
},
|
1860 |
-
{
|
1861 |
-
"id": 279,
|
1862 |
-
"content": "<|unused134|>",
|
1863 |
-
"single_word": false,
|
1864 |
-
"lstrip": false,
|
1865 |
-
"rstrip": false,
|
1866 |
-
"normalized": false,
|
1867 |
-
"special": true
|
1868 |
-
},
|
1869 |
-
{
|
1870 |
-
"id": 280,
|
1871 |
-
"content": "<|unused135|>",
|
1872 |
-
"single_word": false,
|
1873 |
-
"lstrip": false,
|
1874 |
-
"rstrip": false,
|
1875 |
-
"normalized": false,
|
1876 |
-
"special": true
|
1877 |
-
},
|
1878 |
-
{
|
1879 |
-
"id": 281,
|
1880 |
-
"content": "<|unused136|>",
|
1881 |
-
"single_word": false,
|
1882 |
-
"lstrip": false,
|
1883 |
-
"rstrip": false,
|
1884 |
-
"normalized": false,
|
1885 |
-
"special": true
|
1886 |
-
},
|
1887 |
-
{
|
1888 |
-
"id": 282,
|
1889 |
-
"content": "<|unused137|>",
|
1890 |
-
"single_word": false,
|
1891 |
-
"lstrip": false,
|
1892 |
-
"rstrip": false,
|
1893 |
-
"normalized": false,
|
1894 |
-
"special": true
|
1895 |
-
},
|
1896 |
-
{
|
1897 |
-
"id": 283,
|
1898 |
-
"content": "<|unused138|>",
|
1899 |
-
"single_word": false,
|
1900 |
-
"lstrip": false,
|
1901 |
-
"rstrip": false,
|
1902 |
-
"normalized": false,
|
1903 |
-
"special": true
|
1904 |
-
},
|
1905 |
-
{
|
1906 |
-
"id": 284,
|
1907 |
-
"content": "<|unused139|>",
|
1908 |
-
"single_word": false,
|
1909 |
-
"lstrip": false,
|
1910 |
-
"rstrip": false,
|
1911 |
-
"normalized": false,
|
1912 |
-
"special": true
|
1913 |
-
},
|
1914 |
-
{
|
1915 |
-
"id": 285,
|
1916 |
-
"content": "<|unused140|>",
|
1917 |
-
"single_word": false,
|
1918 |
-
"lstrip": false,
|
1919 |
-
"rstrip": false,
|
1920 |
-
"normalized": false,
|
1921 |
-
"special": true
|
1922 |
-
},
|
1923 |
-
{
|
1924 |
-
"id": 286,
|
1925 |
-
"content": "<|unused141|>",
|
1926 |
-
"single_word": false,
|
1927 |
-
"lstrip": false,
|
1928 |
-
"rstrip": false,
|
1929 |
-
"normalized": false,
|
1930 |
-
"special": true
|
1931 |
-
},
|
1932 |
-
{
|
1933 |
-
"id": 287,
|
1934 |
-
"content": "<|unused142|>",
|
1935 |
-
"single_word": false,
|
1936 |
-
"lstrip": false,
|
1937 |
-
"rstrip": false,
|
1938 |
-
"normalized": false,
|
1939 |
-
"special": true
|
1940 |
-
},
|
1941 |
-
{
|
1942 |
-
"id": 288,
|
1943 |
-
"content": "<|unused143|>",
|
1944 |
-
"single_word": false,
|
1945 |
-
"lstrip": false,
|
1946 |
-
"rstrip": false,
|
1947 |
-
"normalized": false,
|
1948 |
-
"special": true
|
1949 |
-
},
|
1950 |
-
{
|
1951 |
-
"id": 289,
|
1952 |
-
"content": "<|unused144|>",
|
1953 |
-
"single_word": false,
|
1954 |
-
"lstrip": false,
|
1955 |
-
"rstrip": false,
|
1956 |
-
"normalized": false,
|
1957 |
-
"special": true
|
1958 |
-
},
|
1959 |
-
{
|
1960 |
-
"id": 290,
|
1961 |
-
"content": "<|unused145|>",
|
1962 |
-
"single_word": false,
|
1963 |
-
"lstrip": false,
|
1964 |
-
"rstrip": false,
|
1965 |
-
"normalized": false,
|
1966 |
-
"special": true
|
1967 |
-
},
|
1968 |
-
{
|
1969 |
-
"id": 291,
|
1970 |
-
"content": "<|unused146|>",
|
1971 |
-
"single_word": false,
|
1972 |
-
"lstrip": false,
|
1973 |
-
"rstrip": false,
|
1974 |
-
"normalized": false,
|
1975 |
-
"special": true
|
1976 |
-
},
|
1977 |
-
{
|
1978 |
-
"id": 292,
|
1979 |
-
"content": "<|unused147|>",
|
1980 |
-
"single_word": false,
|
1981 |
-
"lstrip": false,
|
1982 |
-
"rstrip": false,
|
1983 |
-
"normalized": false,
|
1984 |
-
"special": true
|
1985 |
-
},
|
1986 |
-
{
|
1987 |
-
"id": 293,
|
1988 |
-
"content": "<|unused148|>",
|
1989 |
-
"single_word": false,
|
1990 |
-
"lstrip": false,
|
1991 |
-
"rstrip": false,
|
1992 |
-
"normalized": false,
|
1993 |
-
"special": true
|
1994 |
-
},
|
1995 |
-
{
|
1996 |
-
"id": 294,
|
1997 |
-
"content": "<|unused149|>",
|
1998 |
-
"single_word": false,
|
1999 |
-
"lstrip": false,
|
2000 |
-
"rstrip": false,
|
2001 |
-
"normalized": false,
|
2002 |
-
"special": true
|
2003 |
-
},
|
2004 |
-
{
|
2005 |
-
"id": 295,
|
2006 |
-
"content": "<|unused150|>",
|
2007 |
-
"single_word": false,
|
2008 |
-
"lstrip": false,
|
2009 |
-
"rstrip": false,
|
2010 |
-
"normalized": false,
|
2011 |
-
"special": true
|
2012 |
-
},
|
2013 |
-
{
|
2014 |
-
"id": 296,
|
2015 |
-
"content": "<|unused151|>",
|
2016 |
-
"single_word": false,
|
2017 |
-
"lstrip": false,
|
2018 |
-
"rstrip": false,
|
2019 |
-
"normalized": false,
|
2020 |
-
"special": true
|
2021 |
-
},
|
2022 |
-
{
|
2023 |
-
"id": 297,
|
2024 |
-
"content": "<|unused152|>",
|
2025 |
-
"single_word": false,
|
2026 |
-
"lstrip": false,
|
2027 |
-
"rstrip": false,
|
2028 |
-
"normalized": false,
|
2029 |
-
"special": true
|
2030 |
-
},
|
2031 |
-
{
|
2032 |
-
"id": 298,
|
2033 |
-
"content": "<|unused153|>",
|
2034 |
-
"single_word": false,
|
2035 |
-
"lstrip": false,
|
2036 |
-
"rstrip": false,
|
2037 |
-
"normalized": false,
|
2038 |
-
"special": true
|
2039 |
-
},
|
2040 |
-
{
|
2041 |
-
"id": 299,
|
2042 |
-
"content": "<|unused154|>",
|
2043 |
-
"single_word": false,
|
2044 |
-
"lstrip": false,
|
2045 |
-
"rstrip": false,
|
2046 |
-
"normalized": false,
|
2047 |
-
"special": true
|
2048 |
-
},
|
2049 |
-
{
|
2050 |
-
"id": 300,
|
2051 |
-
"content": "<|unused155|>",
|
2052 |
-
"single_word": false,
|
2053 |
-
"lstrip": false,
|
2054 |
-
"rstrip": false,
|
2055 |
-
"normalized": false,
|
2056 |
-
"special": true
|
2057 |
-
},
|
2058 |
-
{
|
2059 |
-
"id": 301,
|
2060 |
-
"content": "<|unused156|>",
|
2061 |
-
"single_word": false,
|
2062 |
-
"lstrip": false,
|
2063 |
-
"rstrip": false,
|
2064 |
-
"normalized": false,
|
2065 |
-
"special": true
|
2066 |
-
},
|
2067 |
-
{
|
2068 |
-
"id": 302,
|
2069 |
-
"content": "<|unused157|>",
|
2070 |
-
"single_word": false,
|
2071 |
-
"lstrip": false,
|
2072 |
-
"rstrip": false,
|
2073 |
-
"normalized": false,
|
2074 |
-
"special": true
|
2075 |
-
},
|
2076 |
-
{
|
2077 |
-
"id": 303,
|
2078 |
-
"content": "<|unused158|>",
|
2079 |
-
"single_word": false,
|
2080 |
-
"lstrip": false,
|
2081 |
-
"rstrip": false,
|
2082 |
-
"normalized": false,
|
2083 |
-
"special": true
|
2084 |
-
},
|
2085 |
-
{
|
2086 |
-
"id": 304,
|
2087 |
-
"content": "<|unused159|>",
|
2088 |
-
"single_word": false,
|
2089 |
-
"lstrip": false,
|
2090 |
-
"rstrip": false,
|
2091 |
-
"normalized": false,
|
2092 |
-
"special": true
|
2093 |
}
|
2094 |
],
|
2095 |
"normalizer": {
|
@@ -2121,12 +60,6 @@
|
|
2121 |
},
|
2122 |
{
|
2123 |
"type": "Fuse"
|
2124 |
-
},
|
2125 |
-
{
|
2126 |
-
"type": "Strip",
|
2127 |
-
"content": " ",
|
2128 |
-
"start": 1,
|
2129 |
-
"stop": 0
|
2130 |
}
|
2131 |
]
|
2132 |
},
|
@@ -2142,9 +75,17 @@
|
|
2142 |
"<unk>": 0,
|
2143 |
"<|startoftext|>": 1,
|
2144 |
"<|endoftext|>": 2,
|
|
|
|
|
|
|
2145 |
"<|im_start|>": 6,
|
2146 |
"<|im_end|>": 7,
|
2147 |
"<|im_sep|>": 8,
|
|
|
|
|
|
|
|
|
|
|
2148 |
"<fim_prefix>": 14,
|
2149 |
"<fim_middle>": 15,
|
2150 |
"<fim_suffix>": 16,
|
@@ -176164,4 +174105,4 @@
|
|
176164 |
"现 今"
|
176165 |
]
|
176166 |
}
|
176167 |
-
}
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
|
|
60 |
},
|
61 |
{
|
62 |
"type": "Fuse"
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
]
|
65 |
},
|
|
|
75 |
"<unk>": 0,
|
76 |
"<|startoftext|>": 1,
|
77 |
"<|endoftext|>": 2,
|
78 |
+
"<|Human|>": 3,
|
79 |
+
"<|Assistant|>": 4,
|
80 |
+
"<|System|>": 5,
|
81 |
"<|im_start|>": 6,
|
82 |
"<|im_end|>": 7,
|
83 |
"<|im_sep|>": 8,
|
84 |
+
"<|reserved003|>": 9,
|
85 |
+
"<|reserved004|>": 10,
|
86 |
+
"<|reserved005|>": 11,
|
87 |
+
"<|reserved006|>": 12,
|
88 |
+
"<|reserved007|>": 13,
|
89 |
"<fim_prefix>": 14,
|
90 |
"<fim_middle>": 15,
|
91 |
"<fim_suffix>": 16,
|
|
|
174105 |
"现 今"
|
174106 |
]
|
174107 |
}
|
174108 |
+
}
|