PiPiii commited on
Commit
1cf15f0
·
verified ·
1 Parent(s): b368b33

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -1,35 +1,2 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
  *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  *.safetensors filter=lfs diff=lfs merge=lfs -text
2
+ tokenizer.model filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
LICENSE ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 (c) 2025 Baidu, Inc. All Rights Reserved.
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.
202
+
README.md ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - zh
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - ERNIE4.5
9
+ ---
10
+
11
+ <div align="center" style="line-height: 1;">
12
+ <a href="https://ernie.baidu.com/" target="_blank" style="margin: 2px;">
13
+ <img alt="Chat" src="https://img.shields.io/badge/🤖_Chat-ERNIE_Bot-blue" style="display: inline-block; vertical-align: middle;"/>
14
+ </a>
15
+ <a href="https://huggingface.co/baidu" target="_blank" style="margin: 2px;">
16
+ <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Baidu-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
17
+ </a>
18
+ <a href="https://github.com/PaddlePaddle/ERNIE" target="_blank" style="margin: 2px;">
19
+ <img alt="Github" src="https://img.shields.io/badge/GitHub-ERNIE-000?logo=github&color=0000FF" style="display: inline-block; vertical-align: middle;"/>
20
+ </a>
21
+ <a href="https://ernie.baidu.com/blog/ernie4.5" target="_blank" style="margin: 2px;">
22
+ <img alt="Blog" src="https://img.shields.io/badge/🖖_Blog-ERNIE4.5-A020A0" style="display: inline-block; vertical-align: middle;"/>
23
+ </a>
24
+ </div>
25
+
26
+ <div align="center" style="line-height: 1;">
27
+ <a href="#license" style="margin: 2px;">
28
+ <img alt="License" src="https://img.shields.io/badge/License-Apache2.0-A5de54" style="display: inline-block; vertical-align: middle;"/>
29
+ </a>
30
+ </div>
31
+
32
+ # ERNIE-4.5-300B-A47B
33
+
34
+ ## ERNIE 4.5 Highlights
35
+
36
+ The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
37
+
38
+ 1. **Multimodal Heterogeneous MoE Pre-Training:** Our models are jointly trained on both textual and visual modalities to better capture the nuances of multimodal information and improve performance on tasks involving text understanding and generation, image understanding, and cross-modal reasoning. To achieve this without one modality hindering the learning of another, we designed a *heterogeneous MoE structure*, incorporated *modality-isolated routing*, and employed *router orthogonal loss* and *multimodal token-balanced loss*. These architectural choices ensure that both modalities are effectively represented, allowing for mutual reinforcement during training.
39
+
40
+ 2. **Scaling-Efficient Infrastructure:** We propose a novel heterogeneous hybrid parallelism and hierarchical load balancing strategy for efficient training of ERNIE 4.5 models. By using intra-node expert parallelism, memory-efficient pipeline scheduling, FP8 mixed-precision training and finegrained recomputation methods, we achieve remarkable pre-training throughput. For inference, we propose *multi-expert parallel collaboration* method and *convolutional code quantization* algorithm to achieve 4-bit/2-bit lossless quantization. Furthermore, we introduce PD disaggregation with dynamic role switching for effective resource utilization to enhance inference performance for ERNIE 4.5 MoE models. Built on [PaddlePaddle](https://github.com/PaddlePaddle/Paddle), ERNIE 4.5 delivers high-performance inference across a wide range of hardware platforms.
41
+
42
+ 3. **Modality-Specific Post-Training:** To meet the diverse requirements of real-world applications, we fine-tuned variants of the pre-trained model for specific modalities. Our LLMs are optimized for general-purpose language understanding and generation. The VLMs focuses on visuallanguage understanding and supports both thinking and non-thinking modes. Each model employed a combination of *Supervised Fine-tuning (SFT)*, *Direct Preference Optimization (DPO)* or a modified reinforcement learning method named *Unified Preference Optimization (UPO)* for post-training.
43
+
44
+ ## Model Overview
45
+
46
+ ERNIE-4.5-300B-A47B is a text MoE Post-trained model, with 300B total parameters and 47B activated parameters for each token. The following are the model configuration details:
47
+
48
+ |Key|Value|
49
+ |-|-|
50
+ |Modality|Text|
51
+ |Training Stage|Pretraining|
52
+ |Params(Total / Activated)|300B / 47B|
53
+ |Layers|54|
54
+ |Heads(Q/KV)|64 / 8|
55
+ |Text Experts(Total / Activated)|64 / 8|
56
+ |Vision Experts(Total / Activated)|64 / 8|
57
+ |Context Length|131072|
58
+
59
+ ## Quickstart
60
+
61
+ ### Using FastDeploy
62
+
63
+ Service deployment can be quickly completed using FastDeploy in the following command. For more detailed usage instructions, please refer to the [FastDeploy Repository](https://github.com/PaddlePaddle/FastDeploy).
64
+
65
+ **Note**: To deploy on a configuration with 4 GPUs each having at least 80G of memory, specify ```--quantization wint4```. If you specify ```--quantization wint8```, then resources for 8 GPUs are required.
66
+
67
+ ```bash
68
+ python -m fastdeploy.entrypoints.openai.api_server \
69
+ --model baidu/ERNIE-4.5-300B-A47B-Paddle \
70
+ --port 8180 \
71
+ --metrics-port 8181 \
72
+ --quantization wint4 \
73
+ --tensor-parallel-size 8 \
74
+ --engine-worker-queue-port 8182 \
75
+ --max-model-len 32768 \
76
+ --max-num-seqs 32
77
+ ```
78
+
79
+ To deploy the W4A8C8 quantized version using FastDeploy, you can run the following command.
80
+
81
+ ```bash
82
+ python -m fastdeploy.entrypoints.openai.api_server \
83
+ --model baidu/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle \
84
+ --port 8180 \
85
+ --metrics-port 8181 \
86
+ --engine-worker-queue-port 8182 \
87
+ --tensor-parallel-size 4 \
88
+ --max-model-len 32768 \
89
+ --max-num-seqs 32
90
+ ```
91
+
92
+ To deploy the WINT2 quantized version using FastDeploy on two 80G GPUs, run the following command.
93
+
94
+
95
+ ```bash
96
+ python -m fastdeploy.entrypoints.openai.api_server \
97
+ --model "baidu/ERNIE-4.5-300B-A47B-2BITS-TP2-Paddle" \
98
+ --port 8180 \
99
+ --metrics-port 8181 \
100
+ --engine-worker-queue-port 8182 \
101
+ --tensor-parallel-size 2 \
102
+ --max-model-len 32768 \
103
+ --max-num-seqs 128
104
+ ```
105
+
106
+ The following contains a code snippet illustrating how to use ERNIE-4.5-300B-A47B-FP8 generate content based on given inputs.
107
+
108
+ ```python
109
+ from fastdeploy import LLM, SamplingParams
110
+
111
+ prompts = [
112
+ "Hello, my name is",
113
+ ]
114
+
115
+ sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=128)
116
+
117
+ model = "baidu/ERNIE-4.5-300B-A47B-FP8-Paddle"
118
+ llm = LLM(model=model, tensor_parallel_size=8, max_model_len=8192, num_gpu_blocks_override=1024, engine_worker_queue_port=9981)
119
+
120
+ outputs = llm.generate(prompts, sampling_params)
121
+
122
+ for output in outputs:
123
+ prompt = output.prompt
124
+ generated_text = output.outputs.text
125
+ print("generated_text", generated_text)
126
+ ```
127
+
128
+ ## Best Practices
129
+
130
+ ### **Sampling Parameters**
131
+
132
+ To achieve optimal performance, we suggest using `Temperature=0.8`, `TopP=0.8`.
133
+
134
+ ### Prompts for Web Search
135
+
136
+ For Web Search, {references}, {date}, and {question} are arguments.
137
+
138
+ For Chinese question, we use the prompt:
139
+
140
+ ```python
141
+ ernie_search_zh_prompt = \
142
+ '''下面你会收到当前时间、多个不同来源的参考文章和一段对话。你的任务是阅读多个参考文章,并根据参考文章中的信息回答对话中的问题。
143
+ 以下是当前时间和参考文章:
144
+ ---------
145
+ #当前时间
146
+ {date}
147
+
148
+ #参考文章
149
+ {references}
150
+
151
+ ---------
152
+ 请注意:
153
+ 1. 回答必须结合问题需求和当前时间,对参考文章的可用性进行判断,避免在回答中使用错误或过时的信息。
154
+ 2. 当参考文章中的信息无法准确地回答问题时,你需要在回答中提供获取相应信息的建议,或承认无法提供相应信息。
155
+ 3. 你需要优先根据百科、官网、权威机构、专业网站等高权威性来源的信息来回答问题。
156
+ 4. 回复需要综合参考文章中的相关数字、案例、法律条文、公式等信息,使你的答案更专业。
157
+ 5. 当问题属于创作类任务时,需注意以下维度:
158
+ - 态度鲜明:观点、立场清晰明确,避免模棱两可,语言果断直接
159
+ - 文采飞扬:用词精准生动,善用修辞手法,增强感染力
160
+ - 有理有据:逻辑严密递进,结合权威数据/事实支撑论点
161
+ ---------
162
+ 下面请结合以上信息,回答问题,补全对话
163
+ {question}'''
164
+ ```
165
+
166
+ For English question, we use the prompt:
167
+
168
+ ```python
169
+ ernie_search_en_prompt = \
170
+ '''
171
+ Below you will be given the current time, multiple references from different sources, and a conversation. Your task is to read the references and use the information in them to answer the question in the conversation.
172
+ Here are the current time and the references:
173
+ ---------
174
+ #Current Time
175
+ {date}
176
+
177
+ #References
178
+ {references}
179
+
180
+ ---------
181
+ Please note:
182
+ 1. Based on the question’s requirements and the current time, assess the usefulness of the references to avoid using inaccurate or outdated information in the answer.
183
+ 2. If the references do not provide enough information to accurately answer the question, you should suggest how to obtain the relevant information or acknowledge that you are unable to provide it.
184
+ 3. Prioritize using information from highly authoritative sources such as encyclopedias, official websites, authoritative institutions, and professional websites when answering questions.
185
+ 4. Incorporate relevant numbers, cases, legal provisions, formulas, and other details from the references to make your answer more professional.
186
+ 5. For creative tasks, keep these dimensions in mind:
187
+ - Clear attitude: Clear views and positions, avoid ambiguity, and use decisive and direct language
188
+ - Brilliant writing: Precise and vivid words, good use of rhetoric, and enhance the appeal
189
+ - Well-reasoned: Rigorous logic and progressive, combined with authoritative data/facts to support the argument
190
+
191
+ ---------
192
+ Now, using the information above, answer the question and complete the conversation:
193
+ {question}'''
194
+ ```
195
+
196
+ Parameter notes:
197
+
198
+ * {question} is the user’s question
199
+ * {date} is the current time, and the recommended format is “YYYY-MM-DD HH:MM:SS, Day of the Week, Beijing/China.”
200
+ * {references} is the references, and the recommended format is:
201
+
202
+ ```text
203
+ ##参考文章1
204
+ 标题:周杰伦
205
+ 文章发布时间:2025-04-20
206
+ 内容:周杰伦(Jay Chou),1979年1月18日出生于台湾省新北市,祖籍福建省永春县,华语流行乐男歌手、音乐人、演���、导演、编剧,毕业于淡江中学。2000年,发行个人首张音乐专辑《Jay》。...
207
+ 来源网站网址:baike.baidu.com
208
+ 来源网站的网站名:百度百科
209
+
210
+ ##参考文章2
211
+ ...
212
+ ```
213
+
214
+ ## License
215
+
216
+ The ERNIE 4.5 models are provided under the Apache License 2.0. This license permits commercial use, subject to its terms and conditions. Copyright (c) 2025 Baidu, Inc. All Rights Reserved.
217
+
218
+ ## Citation
219
+
220
+ If you find ERNIE 4.5 useful or wish to use it in your projects, please kindly cite our technical report:
221
+
222
+ ```bibtex
223
+ @misc{ernie2025technicalreport,
224
+ title={ERNIE 4.5 Technical Report},
225
+ author={Baidu ERNIE Team},
226
+ year={2025},
227
+ eprint={},
228
+ archivePrefix={arXiv},
229
+ primaryClass={cs.CL},
230
+ url={}
231
+ }
232
+ ```
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|IMAGE_PLACEHOLDER|>": 100295, "<|AUDIO_PLACEHOLDER|>": 100296, "<|LOC_0|>": 100297, "<|LOC_1|>": 100298, "<|LOC_2|>": 100299, "<|LOC_3|>": 100300, "<|LOC_4|>": 100301, "<|LOC_5|>": 100302, "<|LOC_6|>": 100303, "<|LOC_7|>": 100304, "<|LOC_8|>": 100305, "<|LOC_9|>": 100306, "<|LOC_10|>": 100307, "<|LOC_11|>": 100308, "<|LOC_12|>": 100309, "<|LOC_13|>": 100310, "<|LOC_14|>": 100311, "<|LOC_15|>": 100312, "<|LOC_16|>": 100313, "<|LOC_17|>": 100314, "<|LOC_18|>": 100315, "<|LOC_19|>": 100316, "<|LOC_20|>": 100317, "<|LOC_21|>": 100318, "<|LOC_22|>": 100319, "<|LOC_23|>": 100320, "<|LOC_24|>": 100321, "<|LOC_25|>": 100322, "<|LOC_26|>": 100323, "<|LOC_27|>": 100324, "<|LOC_28|>": 100325, "<|LOC_29|>": 100326, "<|LOC_30|>": 100327, "<|LOC_31|>": 100328, "<|LOC_32|>": 100329, "<|LOC_33|>": 100330, "<|LOC_34|>": 100331, "<|LOC_35|>": 100332, "<|LOC_36|>": 100333, "<|LOC_37|>": 100334, "<|LOC_38|>": 100335, "<|LOC_39|>": 100336, "<|LOC_40|>": 100337, "<|LOC_41|>": 100338, "<|LOC_42|>": 100339, "<|LOC_43|>": 100340, "<|LOC_44|>": 100341, "<|LOC_45|>": 100342, "<|LOC_46|>": 100343, "<|LOC_47|>": 100344, "<|LOC_48|>": 100345, "<|LOC_49|>": 100346, "<|LOC_50|>": 100347, "<|LOC_51|>": 100348, "<|LOC_52|>": 100349, "<|LOC_53|>": 100350, "<|LOC_54|>": 100351, "<|LOC_55|>": 100352, "<|LOC_56|>": 100353, "<|LOC_57|>": 100354, "<|LOC_58|>": 100355, "<|LOC_59|>": 100356, "<|LOC_60|>": 100357, "<|LOC_61|>": 100358, "<|LOC_62|>": 100359, "<|LOC_63|>": 100360, "<|LOC_64|>": 100361, "<|LOC_65|>": 100362, "<|LOC_66|>": 100363, "<|LOC_67|>": 100364, "<|LOC_68|>": 100365, "<|LOC_69|>": 100366, "<|LOC_70|>": 100367, "<|LOC_71|>": 100368, "<|LOC_72|>": 100369, "<|LOC_73|>": 100370, "<|LOC_74|>": 100371, "<|LOC_75|>": 100372, "<|LOC_76|>": 100373, "<|LOC_77|>": 100374, "<|LOC_78|>": 100375, "<|LOC_79|>": 100376, "<|LOC_80|>": 100377, "<|LOC_81|>": 100378, "<|LOC_82|>": 100379, "<|LOC_83|>": 100380, "<|LOC_84|>": 100381, "<|LOC_85|>": 100382, "<|LOC_86|>": 100383, "<|LOC_87|>": 100384, "<|LOC_88|>": 100385, "<|LOC_89|>": 100386, "<|LOC_90|>": 100387, "<|LOC_91|>": 100388, "<|LOC_92|>": 100389, "<|LOC_93|>": 100390, "<|LOC_94|>": 100391, "<|LOC_95|>": 100392, "<|LOC_96|>": 100393, "<|LOC_97|>": 100394, "<|LOC_98|>": 100395, "<|LOC_99|>": 100396, "<|LOC_100|>": 100397, "<|LOC_101|>": 100398, "<|LOC_102|>": 100399, "<|LOC_103|>": 100400, "<|LOC_104|>": 100401, "<|LOC_105|>": 100402, "<|LOC_106|>": 100403, "<|LOC_107|>": 100404, "<|LOC_108|>": 100405, "<|LOC_109|>": 100406, "<|LOC_110|>": 100407, "<|LOC_111|>": 100408, "<|LOC_112|>": 100409, "<|LOC_113|>": 100410, "<|LOC_114|>": 100411, "<|LOC_115|>": 100412, "<|LOC_116|>": 100413, "<|LOC_117|>": 100414, "<|LOC_118|>": 100415, "<|LOC_119|>": 100416, "<|LOC_120|>": 100417, "<|LOC_121|>": 100418, "<|LOC_122|>": 100419, "<|LOC_123|>": 100420, "<|LOC_124|>": 100421, "<|LOC_125|>": 100422, "<|LOC_126|>": 100423, "<|LOC_127|>": 100424, "<|LOC_128|>": 100425, "<|LOC_129|>": 100426, "<|LOC_130|>": 100427, "<|LOC_131|>": 100428, "<|LOC_132|>": 100429, "<|LOC_133|>": 100430, "<|LOC_134|>": 100431, "<|LOC_135|>": 100432, "<|LOC_136|>": 100433, "<|LOC_137|>": 100434, "<|LOC_138|>": 100435, "<|LOC_139|>": 100436, "<|LOC_140|>": 100437, "<|LOC_141|>": 100438, "<|LOC_142|>": 100439, "<|LOC_143|>": 100440, "<|LOC_144|>": 100441, "<|LOC_145|>": 100442, "<|LOC_146|>": 100443, "<|LOC_147|>": 100444, "<|LOC_148|>": 100445, "<|LOC_149|>": 100446, "<|LOC_150|>": 100447, "<|LOC_151|>": 100448, "<|LOC_152|>": 100449, "<|LOC_153|>": 100450, "<|LOC_154|>": 100451, "<|LOC_155|>": 100452, "<|LOC_156|>": 100453, "<|LOC_157|>": 100454, "<|LOC_158|>": 100455, "<|LOC_159|>": 100456, "<|LOC_160|>": 100457, "<|LOC_161|>": 100458, "<|LOC_162|>": 100459, "<|LOC_163|>": 100460, "<|LOC_164|>": 100461, "<|LOC_165|>": 100462, "<|LOC_166|>": 100463, "<|LOC_167|>": 100464, "<|LOC_168|>": 100465, "<|LOC_169|>": 100466, "<|LOC_170|>": 100467, "<|LOC_171|>": 100468, "<|LOC_172|>": 100469, "<|LOC_173|>": 100470, "<|LOC_174|>": 100471, "<|LOC_175|>": 100472, "<|LOC_176|>": 100473, "<|LOC_177|>": 100474, "<|LOC_178|>": 100475, "<|LOC_179|>": 100476, "<|LOC_180|>": 100477, "<|LOC_181|>": 100478, "<|LOC_182|>": 100479, "<|LOC_183|>": 100480, "<|LOC_184|>": 100481, "<|LOC_185|>": 100482, "<|LOC_186|>": 100483, "<|LOC_187|>": 100484, "<|LOC_188|>": 100485, "<|LOC_189|>": 100486, "<|LOC_190|>": 100487, "<|LOC_191|>": 100488, "<|LOC_192|>": 100489, "<|LOC_193|>": 100490, "<|LOC_194|>": 100491, "<|LOC_195|>": 100492, "<|LOC_196|>": 100493, "<|LOC_197|>": 100494, "<|LOC_198|>": 100495, "<|LOC_199|>": 100496, "<|LOC_200|>": 100497, "<|LOC_201|>": 100498, "<|LOC_202|>": 100499, "<|LOC_203|>": 100500, "<|LOC_204|>": 100501, "<|LOC_205|>": 100502, "<|LOC_206|>": 100503, "<|LOC_207|>": 100504, "<|LOC_208|>": 100505, "<|LOC_209|>": 100506, "<|LOC_210|>": 100507, "<|LOC_211|>": 100508, "<|LOC_212|>": 100509, "<|LOC_213|>": 100510, "<|LOC_214|>": 100511, "<|LOC_215|>": 100512, "<|LOC_216|>": 100513, "<|LOC_217|>": 100514, "<|LOC_218|>": 100515, "<|LOC_219|>": 100516, "<|LOC_220|>": 100517, "<|LOC_221|>": 100518, "<|LOC_222|>": 100519, "<|LOC_223|>": 100520, "<|LOC_224|>": 100521, "<|LOC_225|>": 100522, "<|LOC_226|>": 100523, "<|LOC_227|>": 100524, "<|LOC_228|>": 100525, "<|LOC_229|>": 100526, "<|LOC_230|>": 100527, "<|LOC_231|>": 100528, "<|LOC_232|>": 100529, "<|LOC_233|>": 100530, "<|LOC_234|>": 100531, "<|LOC_235|>": 100532, "<|LOC_236|>": 100533, "<|LOC_237|>": 100534, "<|LOC_238|>": 100535, "<|LOC_239|>": 100536, "<|LOC_240|>": 100537, "<|LOC_241|>": 100538, "<|LOC_242|>": 100539, "<|LOC_243|>": 100540, "<|LOC_244|>": 100541, "<|LOC_245|>": 100542, "<|LOC_246|>": 100543, "<|LOC_247|>": 100544, "<|LOC_248|>": 100545, "<|LOC_249|>": 100546, "<|LOC_250|>": 100547, "<|LOC_251|>": 100548, "<|LOC_252|>": 100549, "<|LOC_253|>": 100550, "<|LOC_254|>": 100551, "<|LOC_255|>": 100552, "<|LOC_256|>": 100553, "<|LOC_257|>": 100554, "<|LOC_258|>": 100555, "<|LOC_259|>": 100556, "<|LOC_260|>": 100557, "<|LOC_261|>": 100558, "<|LOC_262|>": 100559, "<|LOC_263|>": 100560, "<|LOC_264|>": 100561, "<|LOC_265|>": 100562, "<|LOC_266|>": 100563, "<|LOC_267|>": 100564, "<|LOC_268|>": 100565, "<|LOC_269|>": 100566, "<|LOC_270|>": 100567, "<|LOC_271|>": 100568, "<|LOC_272|>": 100569, "<|LOC_273|>": 100570, "<|LOC_274|>": 100571, "<|LOC_275|>": 100572, "<|LOC_276|>": 100573, "<|LOC_277|>": 100574, "<|LOC_278|>": 100575, "<|LOC_279|>": 100576, "<|LOC_280|>": 100577, "<|LOC_281|>": 100578, "<|LOC_282|>": 100579, "<|LOC_283|>": 100580, "<|LOC_284|>": 100581, "<|LOC_285|>": 100582, "<|LOC_286|>": 100583, "<|LOC_287|>": 100584, "<|LOC_288|>": 100585, "<|LOC_289|>": 100586, "<|LOC_290|>": 100587, "<|LOC_291|>": 100588, "<|LOC_292|>": 100589, "<|LOC_293|>": 100590, "<|LOC_294|>": 100591, "<|LOC_295|>": 100592, "<|LOC_296|>": 100593, "<|LOC_297|>": 100594, "<|LOC_298|>": 100595, "<|LOC_299|>": 100596, "<|LOC_300|>": 100597, "<|LOC_301|>": 100598, "<|LOC_302|>": 100599, "<|LOC_303|>": 100600, "<|LOC_304|>": 100601, "<|LOC_305|>": 100602, "<|LOC_306|>": 100603, "<|LOC_307|>": 100604, "<|LOC_308|>": 100605, "<|LOC_309|>": 100606, "<|LOC_310|>": 100607, "<|LOC_311|>": 100608, "<|LOC_312|>": 100609, "<|LOC_313|>": 100610, "<|LOC_314|>": 100611, "<|LOC_315|>": 100612, "<|LOC_316|>": 100613, "<|LOC_317|>": 100614, "<|LOC_318|>": 100615, "<|LOC_319|>": 100616, "<|LOC_320|>": 100617, "<|LOC_321|>": 100618, "<|LOC_322|>": 100619, "<|LOC_323|>": 100620, "<|LOC_324|>": 100621, "<|LOC_325|>": 100622, "<|LOC_326|>": 100623, "<|LOC_327|>": 100624, "<|LOC_328|>": 100625, "<|LOC_329|>": 100626, "<|LOC_330|>": 100627, "<|LOC_331|>": 100628, "<|LOC_332|>": 100629, "<|LOC_333|>": 100630, "<|LOC_334|>": 100631, "<|LOC_335|>": 100632, "<|LOC_336|>": 100633, "<|LOC_337|>": 100634, "<|LOC_338|>": 100635, "<|LOC_339|>": 100636, "<|LOC_340|>": 100637, "<|LOC_341|>": 100638, "<|LOC_342|>": 100639, "<|LOC_343|>": 100640, "<|LOC_344|>": 100641, "<|LOC_345|>": 100642, "<|LOC_346|>": 100643, "<|LOC_347|>": 100644, "<|LOC_348|>": 100645, "<|LOC_349|>": 100646, "<|LOC_350|>": 100647, "<|LOC_351|>": 100648, "<|LOC_352|>": 100649, "<|LOC_353|>": 100650, "<|LOC_354|>": 100651, "<|LOC_355|>": 100652, "<|LOC_356|>": 100653, "<|LOC_357|>": 100654, "<|LOC_358|>": 100655, "<|LOC_359|>": 100656, "<|LOC_360|>": 100657, "<|LOC_361|>": 100658, "<|LOC_362|>": 100659, "<|LOC_363|>": 100660, "<|LOC_364|>": 100661, "<|LOC_365|>": 100662, "<|LOC_366|>": 100663, "<|LOC_367|>": 100664, "<|LOC_368|>": 100665, "<|LOC_369|>": 100666, "<|LOC_370|>": 100667, "<|LOC_371|>": 100668, "<|LOC_372|>": 100669, "<|LOC_373|>": 100670, "<|LOC_374|>": 100671, "<|LOC_375|>": 100672, "<|LOC_376|>": 100673, "<|LOC_377|>": 100674, "<|LOC_378|>": 100675, "<|LOC_379|>": 100676, "<|LOC_380|>": 100677, "<|LOC_381|>": 100678, "<|LOC_382|>": 100679, "<|LOC_383|>": 100680, "<|LOC_384|>": 100681, "<|LOC_385|>": 100682, "<|LOC_386|>": 100683, "<|LOC_387|>": 100684, "<|LOC_388|>": 100685, "<|LOC_389|>": 100686, "<|LOC_390|>": 100687, "<|LOC_391|>": 100688, "<|LOC_392|>": 100689, "<|LOC_393|>": 100690, "<|LOC_394|>": 100691, "<|LOC_395|>": 100692, "<|LOC_396|>": 100693, "<|LOC_397|>": 100694, "<|LOC_398|>": 100695, "<|LOC_399|>": 100696, "<|LOC_400|>": 100697, "<|LOC_401|>": 100698, "<|LOC_402|>": 100699, "<|LOC_403|>": 100700, "<|LOC_404|>": 100701, "<|LOC_405|>": 100702, "<|LOC_406|>": 100703, "<|LOC_407|>": 100704, "<|LOC_408|>": 100705, "<|LOC_409|>": 100706, "<|LOC_410|>": 100707, "<|LOC_411|>": 100708, "<|LOC_412|>": 100709, "<|LOC_413|>": 100710, "<|LOC_414|>": 100711, "<|LOC_415|>": 100712, "<|LOC_416|>": 100713, "<|LOC_417|>": 100714, "<|LOC_418|>": 100715, "<|LOC_419|>": 100716, "<|LOC_420|>": 100717, "<|LOC_421|>": 100718, "<|LOC_422|>": 100719, "<|LOC_423|>": 100720, "<|LOC_424|>": 100721, "<|LOC_425|>": 100722, "<|LOC_426|>": 100723, "<|LOC_427|>": 100724, "<|LOC_428|>": 100725, "<|LOC_429|>": 100726, "<|LOC_430|>": 100727, "<|LOC_431|>": 100728, "<|LOC_432|>": 100729, "<|LOC_433|>": 100730, "<|LOC_434|>": 100731, "<|LOC_435|>": 100732, "<|LOC_436|>": 100733, "<|LOC_437|>": 100734, "<|LOC_438|>": 100735, "<|LOC_439|>": 100736, "<|LOC_440|>": 100737, "<|LOC_441|>": 100738, "<|LOC_442|>": 100739, "<|LOC_443|>": 100740, "<|LOC_444|>": 100741, "<|LOC_445|>": 100742, "<|LOC_446|>": 100743, "<|LOC_447|>": 100744, "<|LOC_448|>": 100745, "<|LOC_449|>": 100746, "<|LOC_450|>": 100747, "<|LOC_451|>": 100748, "<|LOC_452|>": 100749, "<|LOC_453|>": 100750, "<|LOC_454|>": 100751, "<|LOC_455|>": 100752, "<|LOC_456|>": 100753, "<|LOC_457|>": 100754, "<|LOC_458|>": 100755, "<|LOC_459|>": 100756, "<|LOC_460|>": 100757, "<|LOC_461|>": 100758, "<|LOC_462|>": 100759, "<|LOC_463|>": 100760, "<|LOC_464|>": 100761, "<|LOC_465|>": 100762, "<|LOC_466|>": 100763, "<|LOC_467|>": 100764, "<|LOC_468|>": 100765, "<|LOC_469|>": 100766, "<|LOC_470|>": 100767, "<|LOC_471|>": 100768, "<|LOC_472|>": 100769, "<|LOC_473|>": 100770, "<|LOC_474|>": 100771, "<|LOC_475|>": 100772, "<|LOC_476|>": 100773, "<|LOC_477|>": 100774, "<|LOC_478|>": 100775, "<|LOC_479|>": 100776, "<|LOC_480|>": 100777, "<|LOC_481|>": 100778, "<|LOC_482|>": 100779, "<|LOC_483|>": 100780, "<|LOC_484|>": 100781, "<|LOC_485|>": 100782, "<|LOC_486|>": 100783, "<|LOC_487|>": 100784, "<|LOC_488|>": 100785, "<|LOC_489|>": 100786, "<|LOC_490|>": 100787, "<|LOC_491|>": 100788, "<|LOC_492|>": 100789, "<|LOC_493|>": 100790, "<|LOC_494|>": 100791, "<|LOC_495|>": 100792, "<|LOC_496|>": 100793, "<|LOC_497|>": 100794, "<|LOC_498|>": 100795, "<|LOC_499|>": 100796, "<|LOC_500|>": 100797, "<|LOC_501|>": 100798, "<|LOC_502|>": 100799, "<|LOC_503|>": 100800, "<|LOC_504|>": 100801, "<|LOC_505|>": 100802, "<|LOC_506|>": 100803, "<|LOC_507|>": 100804, "<|LOC_508|>": 100805, "<|LOC_509|>": 100806, "<|LOC_510|>": 100807, "<|LOC_511|>": 100808, "<|LOC_512|>": 100809, "<|LOC_513|>": 100810, "<|LOC_514|>": 100811, "<|LOC_515|>": 100812, "<|LOC_516|>": 100813, "<|LOC_517|>": 100814, "<|LOC_518|>": 100815, "<|LOC_519|>": 100816, "<|LOC_520|>": 100817, "<|LOC_521|>": 100818, "<|LOC_522|>": 100819, "<|LOC_523|>": 100820, "<|LOC_524|>": 100821, "<|LOC_525|>": 100822, "<|LOC_526|>": 100823, "<|LOC_527|>": 100824, "<|LOC_528|>": 100825, "<|LOC_529|>": 100826, "<|LOC_530|>": 100827, "<|LOC_531|>": 100828, "<|LOC_532|>": 100829, "<|LOC_533|>": 100830, "<|LOC_534|>": 100831, "<|LOC_535|>": 100832, "<|LOC_536|>": 100833, "<|LOC_537|>": 100834, "<|LOC_538|>": 100835, "<|LOC_539|>": 100836, "<|LOC_540|>": 100837, "<|LOC_541|>": 100838, "<|LOC_542|>": 100839, "<|LOC_543|>": 100840, "<|LOC_544|>": 100841, "<|LOC_545|>": 100842, "<|LOC_546|>": 100843, "<|LOC_547|>": 100844, "<|LOC_548|>": 100845, "<|LOC_549|>": 100846, "<|LOC_550|>": 100847, "<|LOC_551|>": 100848, "<|LOC_552|>": 100849, "<|LOC_553|>": 100850, "<|LOC_554|>": 100851, "<|LOC_555|>": 100852, "<|LOC_556|>": 100853, "<|LOC_557|>": 100854, "<|LOC_558|>": 100855, "<|LOC_559|>": 100856, "<|LOC_560|>": 100857, "<|LOC_561|>": 100858, "<|LOC_562|>": 100859, "<|LOC_563|>": 100860, "<|LOC_564|>": 100861, "<|LOC_565|>": 100862, "<|LOC_566|>": 100863, "<|LOC_567|>": 100864, "<|LOC_568|>": 100865, "<|LOC_569|>": 100866, "<|LOC_570|>": 100867, "<|LOC_571|>": 100868, "<|LOC_572|>": 100869, "<|LOC_573|>": 100870, "<|LOC_574|>": 100871, "<|LOC_575|>": 100872, "<|LOC_576|>": 100873, "<|LOC_577|>": 100874, "<|LOC_578|>": 100875, "<|LOC_579|>": 100876, "<|LOC_580|>": 100877, "<|LOC_581|>": 100878, "<|LOC_582|>": 100879, "<|LOC_583|>": 100880, "<|LOC_584|>": 100881, "<|LOC_585|>": 100882, "<|LOC_586|>": 100883, "<|LOC_587|>": 100884, "<|LOC_588|>": 100885, "<|LOC_589|>": 100886, "<|LOC_590|>": 100887, "<|LOC_591|>": 100888, "<|LOC_592|>": 100889, "<|LOC_593|>": 100890, "<|LOC_594|>": 100891, "<|LOC_595|>": 100892, "<|LOC_596|>": 100893, "<|LOC_597|>": 100894, "<|LOC_598|>": 100895, "<|LOC_599|>": 100896, "<|LOC_600|>": 100897, "<|LOC_601|>": 100898, "<|LOC_602|>": 100899, "<|LOC_603|>": 100900, "<|LOC_604|>": 100901, "<|LOC_605|>": 100902, "<|LOC_606|>": 100903, "<|LOC_607|>": 100904, "<|LOC_608|>": 100905, "<|LOC_609|>": 100906, "<|LOC_610|>": 100907, "<|LOC_611|>": 100908, "<|LOC_612|>": 100909, "<|LOC_613|>": 100910, "<|LOC_614|>": 100911, "<|LOC_615|>": 100912, "<|LOC_616|>": 100913, "<|LOC_617|>": 100914, "<|LOC_618|>": 100915, "<|LOC_619|>": 100916, "<|LOC_620|>": 100917, "<|LOC_621|>": 100918, "<|LOC_622|>": 100919, "<|LOC_623|>": 100920, "<|LOC_624|>": 100921, "<|LOC_625|>": 100922, "<|LOC_626|>": 100923, "<|LOC_627|>": 100924, "<|LOC_628|>": 100925, "<|LOC_629|>": 100926, "<|LOC_630|>": 100927, "<|LOC_631|>": 100928, "<|LOC_632|>": 100929, "<|LOC_633|>": 100930, "<|LOC_634|>": 100931, "<|LOC_635|>": 100932, "<|LOC_636|>": 100933, "<|LOC_637|>": 100934, "<|LOC_638|>": 100935, "<|LOC_639|>": 100936, "<|LOC_640|>": 100937, "<|LOC_641|>": 100938, "<|LOC_642|>": 100939, "<|LOC_643|>": 100940, "<|LOC_644|>": 100941, "<|LOC_645|>": 100942, "<|LOC_646|>": 100943, "<|LOC_647|>": 100944, "<|LOC_648|>": 100945, "<|LOC_649|>": 100946, "<|LOC_650|>": 100947, "<|LOC_651|>": 100948, "<|LOC_652|>": 100949, "<|LOC_653|>": 100950, "<|LOC_654|>": 100951, "<|LOC_655|>": 100952, "<|LOC_656|>": 100953, "<|LOC_657|>": 100954, "<|LOC_658|>": 100955, "<|LOC_659|>": 100956, "<|LOC_660|>": 100957, "<|LOC_661|>": 100958, "<|LOC_662|>": 100959, "<|LOC_663|>": 100960, "<|LOC_664|>": 100961, "<|LOC_665|>": 100962, "<|LOC_666|>": 100963, "<|LOC_667|>": 100964, "<|LOC_668|>": 100965, "<|LOC_669|>": 100966, "<|LOC_670|>": 100967, "<|LOC_671|>": 100968, "<|LOC_672|>": 100969, "<|LOC_673|>": 100970, "<|LOC_674|>": 100971, "<|LOC_675|>": 100972, "<|LOC_676|>": 100973, "<|LOC_677|>": 100974, "<|LOC_678|>": 100975, "<|LOC_679|>": 100976, "<|LOC_680|>": 100977, "<|LOC_681|>": 100978, "<|LOC_682|>": 100979, "<|LOC_683|>": 100980, "<|LOC_684|>": 100981, "<|LOC_685|>": 100982, "<|LOC_686|>": 100983, "<|LOC_687|>": 100984, "<|LOC_688|>": 100985, "<|LOC_689|>": 100986, "<|LOC_690|>": 100987, "<|LOC_691|>": 100988, "<|LOC_692|>": 100989, "<|LOC_693|>": 100990, "<|LOC_694|>": 100991, "<|LOC_695|>": 100992, "<|LOC_696|>": 100993, "<|LOC_697|>": 100994, "<|LOC_698|>": 100995, "<|LOC_699|>": 100996, "<|LOC_700|>": 100997, "<|LOC_701|>": 100998, "<|LOC_702|>": 100999, "<|LOC_703|>": 101000, "<|LOC_704|>": 101001, "<|LOC_705|>": 101002, "<|LOC_706|>": 101003, "<|LOC_707|>": 101004, "<|LOC_708|>": 101005, "<|LOC_709|>": 101006, "<|LOC_710|>": 101007, "<|LOC_711|>": 101008, "<|LOC_712|>": 101009, "<|LOC_713|>": 101010, "<|LOC_714|>": 101011, "<|LOC_715|>": 101012, "<|LOC_716|>": 101013, "<|LOC_717|>": 101014, "<|LOC_718|>": 101015, "<|LOC_719|>": 101016, "<|LOC_720|>": 101017, "<|LOC_721|>": 101018, "<|LOC_722|>": 101019, "<|LOC_723|>": 101020, "<|LOC_724|>": 101021, "<|LOC_725|>": 101022, "<|LOC_726|>": 101023, "<|LOC_727|>": 101024, "<|LOC_728|>": 101025, "<|LOC_729|>": 101026, "<|LOC_730|>": 101027, "<|LOC_731|>": 101028, "<|LOC_732|>": 101029, "<|LOC_733|>": 101030, "<|LOC_734|>": 101031, "<|LOC_735|>": 101032, "<|LOC_736|>": 101033, "<|LOC_737|>": 101034, "<|LOC_738|>": 101035, "<|LOC_739|>": 101036, "<|LOC_740|>": 101037, "<|LOC_741|>": 101038, "<|LOC_742|>": 101039, "<|LOC_743|>": 101040, "<|LOC_744|>": 101041, "<|LOC_745|>": 101042, "<|LOC_746|>": 101043, "<|LOC_747|>": 101044, "<|LOC_748|>": 101045, "<|LOC_749|>": 101046, "<|LOC_750|>": 101047, "<|LOC_751|>": 101048, "<|LOC_752|>": 101049, "<|LOC_753|>": 101050, "<|LOC_754|>": 101051, "<|LOC_755|>": 101052, "<|LOC_756|>": 101053, "<|LOC_757|>": 101054, "<|LOC_758|>": 101055, "<|LOC_759|>": 101056, "<|LOC_760|>": 101057, "<|LOC_761|>": 101058, "<|LOC_762|>": 101059, "<|LOC_763|>": 101060, "<|LOC_764|>": 101061, "<|LOC_765|>": 101062, "<|LOC_766|>": 101063, "<|LOC_767|>": 101064, "<|LOC_768|>": 101065, "<|LOC_769|>": 101066, "<|LOC_770|>": 101067, "<|LOC_771|>": 101068, "<|LOC_772|>": 101069, "<|LOC_773|>": 101070, "<|LOC_774|>": 101071, "<|LOC_775|>": 101072, "<|LOC_776|>": 101073, "<|LOC_777|>": 101074, "<|LOC_778|>": 101075, "<|LOC_779|>": 101076, "<|LOC_780|>": 101077, "<|LOC_781|>": 101078, "<|LOC_782|>": 101079, "<|LOC_783|>": 101080, "<|LOC_784|>": 101081, "<|LOC_785|>": 101082, "<|LOC_786|>": 101083, "<|LOC_787|>": 101084, "<|LOC_788|>": 101085, "<|LOC_789|>": 101086, "<|LOC_790|>": 101087, "<|LOC_791|>": 101088, "<|LOC_792|>": 101089, "<|LOC_793|>": 101090, "<|LOC_794|>": 101091, "<|LOC_795|>": 101092, "<|LOC_796|>": 101093, "<|LOC_797|>": 101094, "<|LOC_798|>": 101095, "<|LOC_799|>": 101096, "<|LOC_800|>": 101097, "<|LOC_801|>": 101098, "<|LOC_802|>": 101099, "<|LOC_803|>": 101100, "<|LOC_804|>": 101101, "<|LOC_805|>": 101102, "<|LOC_806|>": 101103, "<|LOC_807|>": 101104, "<|LOC_808|>": 101105, "<|LOC_809|>": 101106, "<|LOC_810|>": 101107, "<|LOC_811|>": 101108, "<|LOC_812|>": 101109, "<|LOC_813|>": 101110, "<|LOC_814|>": 101111, "<|LOC_815|>": 101112, "<|LOC_816|>": 101113, "<|LOC_817|>": 101114, "<|LOC_818|>": 101115, "<|LOC_819|>": 101116, "<|LOC_820|>": 101117, "<|LOC_821|>": 101118, "<|LOC_822|>": 101119, "<|LOC_823|>": 101120, "<|LOC_824|>": 101121, "<|LOC_825|>": 101122, "<|LOC_826|>": 101123, "<|LOC_827|>": 101124, "<|LOC_828|>": 101125, "<|LOC_829|>": 101126, "<|LOC_830|>": 101127, "<|LOC_831|>": 101128, "<|LOC_832|>": 101129, "<|LOC_833|>": 101130, "<|LOC_834|>": 101131, "<|LOC_835|>": 101132, "<|LOC_836|>": 101133, "<|LOC_837|>": 101134, "<|LOC_838|>": 101135, "<|LOC_839|>": 101136, "<|LOC_840|>": 101137, "<|LOC_841|>": 101138, "<|LOC_842|>": 101139, "<|LOC_843|>": 101140, "<|LOC_844|>": 101141, "<|LOC_845|>": 101142, "<|LOC_846|>": 101143, "<|LOC_847|>": 101144, "<|LOC_848|>": 101145, "<|LOC_849|>": 101146, "<|LOC_850|>": 101147, "<|LOC_851|>": 101148, "<|LOC_852|>": 101149, "<|LOC_853|>": 101150, "<|LOC_854|>": 101151, "<|LOC_855|>": 101152, "<|LOC_856|>": 101153, "<|LOC_857|>": 101154, "<|LOC_858|>": 101155, "<|LOC_859|>": 101156, "<|LOC_860|>": 101157, "<|LOC_861|>": 101158, "<|LOC_862|>": 101159, "<|LOC_863|>": 101160, "<|LOC_864|>": 101161, "<|LOC_865|>": 101162, "<|LOC_866|>": 101163, "<|LOC_867|>": 101164, "<|LOC_868|>": 101165, "<|LOC_869|>": 101166, "<|LOC_870|>": 101167, "<|LOC_871|>": 101168, "<|LOC_872|>": 101169, "<|LOC_873|>": 101170, "<|LOC_874|>": 101171, "<|LOC_875|>": 101172, "<|LOC_876|>": 101173, "<|LOC_877|>": 101174, "<|LOC_878|>": 101175, "<|LOC_879|>": 101176, "<|LOC_880|>": 101177, "<|LOC_881|>": 101178, "<|LOC_882|>": 101179, "<|LOC_883|>": 101180, "<|LOC_884|>": 101181, "<|LOC_885|>": 101182, "<|LOC_886|>": 101183, "<|LOC_887|>": 101184, "<|LOC_888|>": 101185, "<|LOC_889|>": 101186, "<|LOC_890|>": 101187, "<|LOC_891|>": 101188, "<|LOC_892|>": 101189, "<|LOC_893|>": 101190, "<|LOC_894|>": 101191, "<|LOC_895|>": 101192, "<|LOC_896|>": 101193, "<|LOC_897|>": 101194, "<|LOC_898|>": 101195, "<|LOC_899|>": 101196, "<|LOC_900|>": 101197, "<|LOC_901|>": 101198, "<|LOC_902|>": 101199, "<|LOC_903|>": 101200, "<|LOC_904|>": 101201, "<|LOC_905|>": 101202, "<|LOC_906|>": 101203, "<|LOC_907|>": 101204, "<|LOC_908|>": 101205, "<|LOC_909|>": 101206, "<|LOC_910|>": 101207, "<|LOC_911|>": 101208, "<|LOC_912|>": 101209, "<|LOC_913|>": 101210, "<|LOC_914|>": 101211, "<|LOC_915|>": 101212, "<|LOC_916|>": 101213, "<|LOC_917|>": 101214, "<|LOC_918|>": 101215, "<|LOC_919|>": 101216, "<|LOC_920|>": 101217, "<|LOC_921|>": 101218, "<|LOC_922|>": 101219, "<|LOC_923|>": 101220, "<|LOC_924|>": 101221, "<|LOC_925|>": 101222, "<|LOC_926|>": 101223, "<|LOC_927|>": 101224, "<|LOC_928|>": 101225, "<|LOC_929|>": 101226, "<|LOC_930|>": 101227, "<|LOC_931|>": 101228, "<|LOC_932|>": 101229, "<|LOC_933|>": 101230, "<|LOC_934|>": 101231, "<|LOC_935|>": 101232, "<|LOC_936|>": 101233, "<|LOC_937|>": 101234, "<|LOC_938|>": 101235, "<|LOC_939|>": 101236, "<|LOC_940|>": 101237, "<|LOC_941|>": 101238, "<|LOC_942|>": 101239, "<|LOC_943|>": 101240, "<|LOC_944|>": 101241, "<|LOC_945|>": 101242, "<|LOC_946|>": 101243, "<|LOC_947|>": 101244, "<|LOC_948|>": 101245, "<|LOC_949|>": 101246, "<|LOC_950|>": 101247, "<|LOC_951|>": 101248, "<|LOC_952|>": 101249, "<|LOC_953|>": 101250, "<|LOC_954|>": 101251, "<|LOC_955|>": 101252, "<|LOC_956|>": 101253, "<|LOC_957|>": 101254, "<|LOC_958|>": 101255, "<|LOC_959|>": 101256, "<|LOC_960|>": 101257, "<|LOC_961|>": 101258, "<|LOC_962|>": 101259, "<|LOC_963|>": 101260, "<|LOC_964|>": 101261, "<|LOC_965|>": 101262, "<|LOC_966|>": 101263, "<|LOC_967|>": 101264, "<|LOC_968|>": 101265, "<|LOC_969|>": 101266, "<|LOC_970|>": 101267, "<|LOC_971|>": 101268, "<|LOC_972|>": 101269, "<|LOC_973|>": 101270, "<|LOC_974|>": 101271, "<|LOC_975|>": 101272, "<|LOC_976|>": 101273, "<|LOC_977|>": 101274, "<|LOC_978|>": 101275, "<|LOC_979|>": 101276, "<|LOC_980|>": 101277, "<|LOC_981|>": 101278, "<|LOC_982|>": 101279, "<|LOC_983|>": 101280, "<|LOC_984|>": 101281, "<|LOC_985|>": 101282, "<|LOC_986|>": 101283, "<|LOC_987|>": 101284, "<|LOC_988|>": 101285, "<|LOC_989|>": 101286, "<|LOC_990|>": 101287, "<|LOC_991|>": 101288, "<|LOC_992|>": 101289, "<|LOC_993|>": 101290, "<|LOC_994|>": 101291, "<|LOC_995|>": 101292, "<|LOC_996|>": 101293, "<|LOC_997|>": 101294, "<|LOC_998|>": 101295, "<|LOC_999|>": 101296, "<|LOC_1000|>": 101297, "<|LOC_BEGIN|>": 101298, "<|LOC_END|>": 101299, "<|LOC_SEP|>": 101300, "<|CROP_COL_SEP|>": 101301, "<|CROP_ROW_SEP|>": 101302, "<|IMAGE_SEP|>": 101303}
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Ernie4_5_MoeForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "dtype": "bfloat16",
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "intermediate_size": 28672,
11
+ "max_position_embeddings": 131072,
12
+ "model_type": "ernie4_5_moe",
13
+ "num_attention_heads": 64,
14
+ "num_key_value_heads": 8,
15
+ "num_hidden_layers": 54,
16
+ "pad_token_id": 0,
17
+ "rms_norm_eps": 1e-05,
18
+ "use_cache": false,
19
+ "vocab_size": 103424,
20
+ "rope_theta": 500000,
21
+ "use_rmsnorm": true,
22
+ "use_bias": false,
23
+ "moe_num_experts": 64,
24
+ "moe_layer_start_index": 3,
25
+ "moe_intermediate_size": 3584,
26
+ "moe_capacity": [
27
+ 64,
28
+ 64,
29
+ 64
30
+ ],
31
+ "moe_gate": "topk",
32
+ "moe_k": 8,
33
+ "moe_layer_interval": 1,
34
+ "moe_use_aux_free": true,
35
+ "num_nextn_predict_layers": 1,
36
+ "tie_word_embeddings": false,
37
+ "quantization_config": {
38
+ "dense_quant_type": "wint8",
39
+ "moe_quant_type": "w4w2",
40
+ "quantization": "wint2",
41
+ "moe_quant_config": {
42
+ "moe_w4_quant_config": {
43
+ "quant_type": "wint4",
44
+ "quant_granularity": "per_channel",
45
+ "quant_start_layer": 0,
46
+ "quant_end_layer": 6
47
+ },
48
+ "moe_w2_quant_config": {
49
+ "quant_type": "wint2",
50
+ "quant_granularity": "pp_acc",
51
+ "quant_group_size": 64,
52
+ "quant_start_layer": 7,
53
+ "quant_end_layer": 53
54
+ }
55
+ }
56
+ }
57
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "top_p": 0.8,
3
+ "temperature": 0.8,
4
+ "repetition_penalty": 1.0,
5
+ "frequency_penalty": 0.0,
6
+ "presence_penalty": 0.0
7
+ }
rank0/model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e0ad08efcc0336f13686dcbd9ba559a4433463bce14cebdfbed013ab060cf5
3
+ size 3994994088
rank0/model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9954018fe1c45a1d5e1d616b99095cebbc19032c120cf5170d2a616f8acf88
3
+ size 3999352608
rank0/model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8272769406ff26b721ed384073265cbbb0bf8a8b3308f2804641b268fde98c
3
+ size 3997279200
rank0/model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b52671e5638670da76658491fbac976ba84cd2e45e14c6c1a65e9d8309af79a
3
+ size 3993610488
rank0/model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fef90cb8e97a9fa64cfd2f2cda9d6f83f83a66565d7c57068859a7406dcd07a
3
+ size 3993610512
rank0/model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752b2fcc6e4c042619355097f97ca1aa9411a1d61367b185ac82ed3285f0f00e
3
+ size 3993610536
rank0/model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b42d530ba51b3f5aec8724ce199c99ee10303e3fa9f657fd2fc2f1389836495
3
+ size 3993610552
rank0/model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d905e8b116eeee254575e70c04150a29405b1842fdd26cffaf8cfd342d0df9d7
3
+ size 3993610576
rank0/model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a49ee9394c500d333c18c3f9521b8b338935834ec8adea54359258aaf1e4b58
3
+ size 3993610600
rank0/model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402c03cbd7d6692ef3e9242bbd7d16a8cae7a7526e11848efd4d03bcb5431538
3
+ size 3993610624
rank0/model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aedaee10d92d31ab7780546aad1e42972d391dbdf0253ae6af4cf1c06cd8794
3
+ size 3993610648
rank0/model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333d527d8b796853e86d9dca962ec0fd589f381a1ccc139ad14ea7eb230a7327
3
+ size 3152707224
rank0/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
rank1/model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2dd9d6a5685e7c8ba4c5112a183d163b4116184930b5b74bb1508e298bfb1e
3
+ size 3994994088
rank1/model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f3505cc2facc12aa1c921be7d846b204c69a8f51707c5d3ec0bc39cd47e27d
3
+ size 3999352608
rank1/model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca839249eeb4ebc03e51621cf1bf51ab6dbfd1c2b6bb1db81109135cc69484e
3
+ size 3997279200
rank1/model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b56bb46562ec6636b681b99b0073f311ddb0920392b0414fd4563de660545f4
3
+ size 3993610488
rank1/model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aef7ff15fd8ba76c10a321d7f8f5645e2251b9ee0e8d982cfa4f47309676063
3
+ size 3993610512
rank1/model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d62e0a1b36027c320953dca68dada0d17fa65bb3d02297d2f5f52e5926ae84
3
+ size 3993610536
rank1/model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a012e5802ab9bb49fe2c317e2e13196851bca2eff3a408aeeb6a3d603126738
3
+ size 3993610552
rank1/model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a21f41a26e5d626418f10db408cbb1e22f37c4c8abd257819872f0cfe67b54
3
+ size 3993610576
rank1/model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032c746307a56f81d8c8ef84581dc8ec5acc5507fcce99b6133d4eae98e3c3d5
3
+ size 3993610600
rank1/model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9bf0b630afe98055fe91f89ee81b93bcf4e3851475d0edfa31f4b3b1cd277c0
3
+ size 3993610624
rank1/model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7591939d2b00227d9915e35dccfe6aa250639f3108e4c47e7ec1538e5f2ef30b
3
+ size 3993610648
rank1/model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64312ed569a9c670cdba0561a3ec780060b739bb3339278764de70d634b9d529
3
+ size 3152707224
rank1/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "pad_token": "<unk>", "unk_token": "<unk>", "cls_token": "<|begin_of_sentence|>", "sep_token": "<|end_of_sentence|>", "mask_token": "<mask:1>", "sys_start_token": "<mask:4>", "sys_end_token": "<mask:5>", "header_start_token": "<mask:6>", "header_end_token": "<mask:7>", "additional_special_tokens": ["<|IMAGE_PLACEHOLDER|>", "<|AUDIO_PLACEHOLDER|>", "<|LOC_0|>", "<|LOC_1|>", "<|LOC_2|>", "<|LOC_3|>", "<|LOC_4|>", "<|LOC_5|>", "<|LOC_6|>", "<|LOC_7|>", "<|LOC_8|>", "<|LOC_9|>", "<|LOC_10|>", "<|LOC_11|>", "<|LOC_12|>", "<|LOC_13|>", "<|LOC_14|>", "<|LOC_15|>", "<|LOC_16|>", "<|LOC_17|>", "<|LOC_18|>", "<|LOC_19|>", "<|LOC_20|>", "<|LOC_21|>", "<|LOC_22|>", "<|LOC_23|>", "<|LOC_24|>", "<|LOC_25|>", "<|LOC_26|>", "<|LOC_27|>", "<|LOC_28|>", "<|LOC_29|>", "<|LOC_30|>", "<|LOC_31|>", "<|LOC_32|>", "<|LOC_33|>", "<|LOC_34|>", "<|LOC_35|>", "<|LOC_36|>", "<|LOC_37|>", "<|LOC_38|>", "<|LOC_39|>", "<|LOC_40|>", "<|LOC_41|>", "<|LOC_42|>", "<|LOC_43|>", "<|LOC_44|>", "<|LOC_45|>", "<|LOC_46|>", "<|LOC_47|>", "<|LOC_48|>", "<|LOC_49|>", "<|LOC_50|>", "<|LOC_51|>", "<|LOC_52|>", "<|LOC_53|>", "<|LOC_54|>", "<|LOC_55|>", "<|LOC_56|>", "<|LOC_57|>", "<|LOC_58|>", "<|LOC_59|>", "<|LOC_60|>", "<|LOC_61|>", "<|LOC_62|>", "<|LOC_63|>", "<|LOC_64|>", "<|LOC_65|>", "<|LOC_66|>", "<|LOC_67|>", "<|LOC_68|>", "<|LOC_69|>", "<|LOC_70|>", "<|LOC_71|>", "<|LOC_72|>", "<|LOC_73|>", "<|LOC_74|>", "<|LOC_75|>", "<|LOC_76|>", "<|LOC_77|>", "<|LOC_78|>", "<|LOC_79|>", "<|LOC_80|>", "<|LOC_81|>", "<|LOC_82|>", "<|LOC_83|>", "<|LOC_84|>", "<|LOC_85|>", "<|LOC_86|>", "<|LOC_87|>", "<|LOC_88|>", "<|LOC_89|>", "<|LOC_90|>", "<|LOC_91|>", "<|LOC_92|>", "<|LOC_93|>", "<|LOC_94|>", "<|LOC_95|>", "<|LOC_96|>", "<|LOC_97|>", "<|LOC_98|>", "<|LOC_99|>", "<|LOC_100|>", "<|LOC_101|>", "<|LOC_102|>", "<|LOC_103|>", "<|LOC_104|>", "<|LOC_105|>", "<|LOC_106|>", "<|LOC_107|>", "<|LOC_108|>", "<|LOC_109|>", "<|LOC_110|>", "<|LOC_111|>", "<|LOC_112|>", "<|LOC_113|>", "<|LOC_114|>", "<|LOC_115|>", "<|LOC_116|>", "<|LOC_117|>", "<|LOC_118|>", "<|LOC_119|>", "<|LOC_120|>", "<|LOC_121|>", "<|LOC_122|>", "<|LOC_123|>", "<|LOC_124|>", "<|LOC_125|>", "<|LOC_126|>", "<|LOC_127|>", "<|LOC_128|>", "<|LOC_129|>", "<|LOC_130|>", "<|LOC_131|>", "<|LOC_132|>", "<|LOC_133|>", "<|LOC_134|>", "<|LOC_135|>", "<|LOC_136|>", "<|LOC_137|>", "<|LOC_138|>", "<|LOC_139|>", "<|LOC_140|>", "<|LOC_141|>", "<|LOC_142|>", "<|LOC_143|>", "<|LOC_144|>", "<|LOC_145|>", "<|LOC_146|>", "<|LOC_147|>", "<|LOC_148|>", "<|LOC_149|>", "<|LOC_150|>", "<|LOC_151|>", "<|LOC_152|>", "<|LOC_153|>", "<|LOC_154|>", "<|LOC_155|>", "<|LOC_156|>", "<|LOC_157|>", "<|LOC_158|>", "<|LOC_159|>", "<|LOC_160|>", "<|LOC_161|>", "<|LOC_162|>", "<|LOC_163|>", "<|LOC_164|>", "<|LOC_165|>", "<|LOC_166|>", "<|LOC_167|>", "<|LOC_168|>", "<|LOC_169|>", "<|LOC_170|>", "<|LOC_171|>", "<|LOC_172|>", "<|LOC_173|>", "<|LOC_174|>", "<|LOC_175|>", "<|LOC_176|>", "<|LOC_177|>", "<|LOC_178|>", "<|LOC_179|>", "<|LOC_180|>", "<|LOC_181|>", "<|LOC_182|>", "<|LOC_183|>", "<|LOC_184|>", "<|LOC_185|>", "<|LOC_186|>", "<|LOC_187|>", "<|LOC_188|>", "<|LOC_189|>", "<|LOC_190|>", "<|LOC_191|>", "<|LOC_192|>", "<|LOC_193|>", "<|LOC_194|>", "<|LOC_195|>", "<|LOC_196|>", "<|LOC_197|>", "<|LOC_198|>", "<|LOC_199|>", "<|LOC_200|>", "<|LOC_201|>", "<|LOC_202|>", "<|LOC_203|>", "<|LOC_204|>", "<|LOC_205|>", "<|LOC_206|>", "<|LOC_207|>", "<|LOC_208|>", "<|LOC_209|>", "<|LOC_210|>", "<|LOC_211|>", "<|LOC_212|>", "<|LOC_213|>", "<|LOC_214|>", "<|LOC_215|>", "<|LOC_216|>", "<|LOC_217|>", "<|LOC_218|>", "<|LOC_219|>", "<|LOC_220|>", "<|LOC_221|>", "<|LOC_222|>", "<|LOC_223|>", "<|LOC_224|>", "<|LOC_225|>", "<|LOC_226|>", "<|LOC_227|>", "<|LOC_228|>", "<|LOC_229|>", "<|LOC_230|>", "<|LOC_231|>", "<|LOC_232|>", "<|LOC_233|>", "<|LOC_234|>", "<|LOC_235|>", "<|LOC_236|>", "<|LOC_237|>", "<|LOC_238|>", "<|LOC_239|>", "<|LOC_240|>", "<|LOC_241|>", "<|LOC_242|>", "<|LOC_243|>", "<|LOC_244|>", "<|LOC_245|>", "<|LOC_246|>", "<|LOC_247|>", "<|LOC_248|>", "<|LOC_249|>", "<|LOC_250|>", "<|LOC_251|>", "<|LOC_252|>", "<|LOC_253|>", "<|LOC_254|>", "<|LOC_255|>", "<|LOC_256|>", "<|LOC_257|>", "<|LOC_258|>", "<|LOC_259|>", "<|LOC_260|>", "<|LOC_261|>", "<|LOC_262|>", "<|LOC_263|>", "<|LOC_264|>", "<|LOC_265|>", "<|LOC_266|>", "<|LOC_267|>", "<|LOC_268|>", "<|LOC_269|>", "<|LOC_270|>", "<|LOC_271|>", "<|LOC_272|>", "<|LOC_273|>", "<|LOC_274|>", "<|LOC_275|>", "<|LOC_276|>", "<|LOC_277|>", "<|LOC_278|>", "<|LOC_279|>", "<|LOC_280|>", "<|LOC_281|>", "<|LOC_282|>", "<|LOC_283|>", "<|LOC_284|>", "<|LOC_285|>", "<|LOC_286|>", "<|LOC_287|>", "<|LOC_288|>", "<|LOC_289|>", "<|LOC_290|>", "<|LOC_291|>", "<|LOC_292|>", "<|LOC_293|>", "<|LOC_294|>", "<|LOC_295|>", "<|LOC_296|>", "<|LOC_297|>", "<|LOC_298|>", "<|LOC_299|>", "<|LOC_300|>", "<|LOC_301|>", "<|LOC_302|>", "<|LOC_303|>", "<|LOC_304|>", "<|LOC_305|>", "<|LOC_306|>", "<|LOC_307|>", "<|LOC_308|>", "<|LOC_309|>", "<|LOC_310|>", "<|LOC_311|>", "<|LOC_312|>", "<|LOC_313|>", "<|LOC_314|>", "<|LOC_315|>", "<|LOC_316|>", "<|LOC_317|>", "<|LOC_318|>", "<|LOC_319|>", "<|LOC_320|>", "<|LOC_321|>", "<|LOC_322|>", "<|LOC_323|>", "<|LOC_324|>", "<|LOC_325|>", "<|LOC_326|>", "<|LOC_327|>", "<|LOC_328|>", "<|LOC_329|>", "<|LOC_330|>", "<|LOC_331|>", "<|LOC_332|>", "<|LOC_333|>", "<|LOC_334|>", "<|LOC_335|>", "<|LOC_336|>", "<|LOC_337|>", "<|LOC_338|>", "<|LOC_339|>", "<|LOC_340|>", "<|LOC_341|>", "<|LOC_342|>", "<|LOC_343|>", "<|LOC_344|>", "<|LOC_345|>", "<|LOC_346|>", "<|LOC_347|>", "<|LOC_348|>", "<|LOC_349|>", "<|LOC_350|>", "<|LOC_351|>", "<|LOC_352|>", "<|LOC_353|>", "<|LOC_354|>", "<|LOC_355|>", "<|LOC_356|>", "<|LOC_357|>", "<|LOC_358|>", "<|LOC_359|>", "<|LOC_360|>", "<|LOC_361|>", "<|LOC_362|>", "<|LOC_363|>", "<|LOC_364|>", "<|LOC_365|>", "<|LOC_366|>", "<|LOC_367|>", "<|LOC_368|>", "<|LOC_369|>", "<|LOC_370|>", "<|LOC_371|>", "<|LOC_372|>", "<|LOC_373|>", "<|LOC_374|>", "<|LOC_375|>", "<|LOC_376|>", "<|LOC_377|>", "<|LOC_378|>", "<|LOC_379|>", "<|LOC_380|>", "<|LOC_381|>", "<|LOC_382|>", "<|LOC_383|>", "<|LOC_384|>", "<|LOC_385|>", "<|LOC_386|>", "<|LOC_387|>", "<|LOC_388|>", "<|LOC_389|>", "<|LOC_390|>", "<|LOC_391|>", "<|LOC_392|>", "<|LOC_393|>", "<|LOC_394|>", "<|LOC_395|>", "<|LOC_396|>", "<|LOC_397|>", "<|LOC_398|>", "<|LOC_399|>", "<|LOC_400|>", "<|LOC_401|>", "<|LOC_402|>", "<|LOC_403|>", "<|LOC_404|>", "<|LOC_405|>", "<|LOC_406|>", "<|LOC_407|>", "<|LOC_408|>", "<|LOC_409|>", "<|LOC_410|>", "<|LOC_411|>", "<|LOC_412|>", "<|LOC_413|>", "<|LOC_414|>", "<|LOC_415|>", "<|LOC_416|>", "<|LOC_417|>", "<|LOC_418|>", "<|LOC_419|>", "<|LOC_420|>", "<|LOC_421|>", "<|LOC_422|>", "<|LOC_423|>", "<|LOC_424|>", "<|LOC_425|>", "<|LOC_426|>", "<|LOC_427|>", "<|LOC_428|>", "<|LOC_429|>", "<|LOC_430|>", "<|LOC_431|>", "<|LOC_432|>", "<|LOC_433|>", "<|LOC_434|>", "<|LOC_435|>", "<|LOC_436|>", "<|LOC_437|>", "<|LOC_438|>", "<|LOC_439|>", "<|LOC_440|>", "<|LOC_441|>", "<|LOC_442|>", "<|LOC_443|>", "<|LOC_444|>", "<|LOC_445|>", "<|LOC_446|>", "<|LOC_447|>", "<|LOC_448|>", "<|LOC_449|>", "<|LOC_450|>", "<|LOC_451|>", "<|LOC_452|>", "<|LOC_453|>", "<|LOC_454|>", "<|LOC_455|>", "<|LOC_456|>", "<|LOC_457|>", "<|LOC_458|>", "<|LOC_459|>", "<|LOC_460|>", "<|LOC_461|>", "<|LOC_462|>", "<|LOC_463|>", "<|LOC_464|>", "<|LOC_465|>", "<|LOC_466|>", "<|LOC_467|>", "<|LOC_468|>", "<|LOC_469|>", "<|LOC_470|>", "<|LOC_471|>", "<|LOC_472|>", "<|LOC_473|>", "<|LOC_474|>", "<|LOC_475|>", "<|LOC_476|>", "<|LOC_477|>", "<|LOC_478|>", "<|LOC_479|>", "<|LOC_480|>", "<|LOC_481|>", "<|LOC_482|>", "<|LOC_483|>", "<|LOC_484|>", "<|LOC_485|>", "<|LOC_486|>", "<|LOC_487|>", "<|LOC_488|>", "<|LOC_489|>", "<|LOC_490|>", "<|LOC_491|>", "<|LOC_492|>", "<|LOC_493|>", "<|LOC_494|>", "<|LOC_495|>", "<|LOC_496|>", "<|LOC_497|>", "<|LOC_498|>", "<|LOC_499|>", "<|LOC_500|>", "<|LOC_501|>", "<|LOC_502|>", "<|LOC_503|>", "<|LOC_504|>", "<|LOC_505|>", "<|LOC_506|>", "<|LOC_507|>", "<|LOC_508|>", "<|LOC_509|>", "<|LOC_510|>", "<|LOC_511|>", "<|LOC_512|>", "<|LOC_513|>", "<|LOC_514|>", "<|LOC_515|>", "<|LOC_516|>", "<|LOC_517|>", "<|LOC_518|>", "<|LOC_519|>", "<|LOC_520|>", "<|LOC_521|>", "<|LOC_522|>", "<|LOC_523|>", "<|LOC_524|>", "<|LOC_525|>", "<|LOC_526|>", "<|LOC_527|>", "<|LOC_528|>", "<|LOC_529|>", "<|LOC_530|>", "<|LOC_531|>", "<|LOC_532|>", "<|LOC_533|>", "<|LOC_534|>", "<|LOC_535|>", "<|LOC_536|>", "<|LOC_537|>", "<|LOC_538|>", "<|LOC_539|>", "<|LOC_540|>", "<|LOC_541|>", "<|LOC_542|>", "<|LOC_543|>", "<|LOC_544|>", "<|LOC_545|>", "<|LOC_546|>", "<|LOC_547|>", "<|LOC_548|>", "<|LOC_549|>", "<|LOC_550|>", "<|LOC_551|>", "<|LOC_552|>", "<|LOC_553|>", "<|LOC_554|>", "<|LOC_555|>", "<|LOC_556|>", "<|LOC_557|>", "<|LOC_558|>", "<|LOC_559|>", "<|LOC_560|>", "<|LOC_561|>", "<|LOC_562|>", "<|LOC_563|>", "<|LOC_564|>", "<|LOC_565|>", "<|LOC_566|>", "<|LOC_567|>", "<|LOC_568|>", "<|LOC_569|>", "<|LOC_570|>", "<|LOC_571|>", "<|LOC_572|>", "<|LOC_573|>", "<|LOC_574|>", "<|LOC_575|>", "<|LOC_576|>", "<|LOC_577|>", "<|LOC_578|>", "<|LOC_579|>", "<|LOC_580|>", "<|LOC_581|>", "<|LOC_582|>", "<|LOC_583|>", "<|LOC_584|>", "<|LOC_585|>", "<|LOC_586|>", "<|LOC_587|>", "<|LOC_588|>", "<|LOC_589|>", "<|LOC_590|>", "<|LOC_591|>", "<|LOC_592|>", "<|LOC_593|>", "<|LOC_594|>", "<|LOC_595|>", "<|LOC_596|>", "<|LOC_597|>", "<|LOC_598|>", "<|LOC_599|>", "<|LOC_600|>", "<|LOC_601|>", "<|LOC_602|>", "<|LOC_603|>", "<|LOC_604|>", "<|LOC_605|>", "<|LOC_606|>", "<|LOC_607|>", "<|LOC_608|>", "<|LOC_609|>", "<|LOC_610|>", "<|LOC_611|>", "<|LOC_612|>", "<|LOC_613|>", "<|LOC_614|>", "<|LOC_615|>", "<|LOC_616|>", "<|LOC_617|>", "<|LOC_618|>", "<|LOC_619|>", "<|LOC_620|>", "<|LOC_621|>", "<|LOC_622|>", "<|LOC_623|>", "<|LOC_624|>", "<|LOC_625|>", "<|LOC_626|>", "<|LOC_627|>", "<|LOC_628|>", "<|LOC_629|>", "<|LOC_630|>", "<|LOC_631|>", "<|LOC_632|>", "<|LOC_633|>", "<|LOC_634|>", "<|LOC_635|>", "<|LOC_636|>", "<|LOC_637|>", "<|LOC_638|>", "<|LOC_639|>", "<|LOC_640|>", "<|LOC_641|>", "<|LOC_642|>", "<|LOC_643|>", "<|LOC_644|>", "<|LOC_645|>", "<|LOC_646|>", "<|LOC_647|>", "<|LOC_648|>", "<|LOC_649|>", "<|LOC_650|>", "<|LOC_651|>", "<|LOC_652|>", "<|LOC_653|>", "<|LOC_654|>", "<|LOC_655|>", "<|LOC_656|>", "<|LOC_657|>", "<|LOC_658|>", "<|LOC_659|>", "<|LOC_660|>", "<|LOC_661|>", "<|LOC_662|>", "<|LOC_663|>", "<|LOC_664|>", "<|LOC_665|>", "<|LOC_666|>", "<|LOC_667|>", "<|LOC_668|>", "<|LOC_669|>", "<|LOC_670|>", "<|LOC_671|>", "<|LOC_672|>", "<|LOC_673|>", "<|LOC_674|>", "<|LOC_675|>", "<|LOC_676|>", "<|LOC_677|>", "<|LOC_678|>", "<|LOC_679|>", "<|LOC_680|>", "<|LOC_681|>", "<|LOC_682|>", "<|LOC_683|>", "<|LOC_684|>", "<|LOC_685|>", "<|LOC_686|>", "<|LOC_687|>", "<|LOC_688|>", "<|LOC_689|>", "<|LOC_690|>", "<|LOC_691|>", "<|LOC_692|>", "<|LOC_693|>", "<|LOC_694|>", "<|LOC_695|>", "<|LOC_696|>", "<|LOC_697|>", "<|LOC_698|>", "<|LOC_699|>", "<|LOC_700|>", "<|LOC_701|>", "<|LOC_702|>", "<|LOC_703|>", "<|LOC_704|>", "<|LOC_705|>", "<|LOC_706|>", "<|LOC_707|>", "<|LOC_708|>", "<|LOC_709|>", "<|LOC_710|>", "<|LOC_711|>", "<|LOC_712|>", "<|LOC_713|>", "<|LOC_714|>", "<|LOC_715|>", "<|LOC_716|>", "<|LOC_717|>", "<|LOC_718|>", "<|LOC_719|>", "<|LOC_720|>", "<|LOC_721|>", "<|LOC_722|>", "<|LOC_723|>", "<|LOC_724|>", "<|LOC_725|>", "<|LOC_726|>", "<|LOC_727|>", "<|LOC_728|>", "<|LOC_729|>", "<|LOC_730|>", "<|LOC_731|>", "<|LOC_732|>", "<|LOC_733|>", "<|LOC_734|>", "<|LOC_735|>", "<|LOC_736|>", "<|LOC_737|>", "<|LOC_738|>", "<|LOC_739|>", "<|LOC_740|>", "<|LOC_741|>", "<|LOC_742|>", "<|LOC_743|>", "<|LOC_744|>", "<|LOC_745|>", "<|LOC_746|>", "<|LOC_747|>", "<|LOC_748|>", "<|LOC_749|>", "<|LOC_750|>", "<|LOC_751|>", "<|LOC_752|>", "<|LOC_753|>", "<|LOC_754|>", "<|LOC_755|>", "<|LOC_756|>", "<|LOC_757|>", "<|LOC_758|>", "<|LOC_759|>", "<|LOC_760|>", "<|LOC_761|>", "<|LOC_762|>", "<|LOC_763|>", "<|LOC_764|>", "<|LOC_765|>", "<|LOC_766|>", "<|LOC_767|>", "<|LOC_768|>", "<|LOC_769|>", "<|LOC_770|>", "<|LOC_771|>", "<|LOC_772|>", "<|LOC_773|>", "<|LOC_774|>", "<|LOC_775|>", "<|LOC_776|>", "<|LOC_777|>", "<|LOC_778|>", "<|LOC_779|>", "<|LOC_780|>", "<|LOC_781|>", "<|LOC_782|>", "<|LOC_783|>", "<|LOC_784|>", "<|LOC_785|>", "<|LOC_786|>", "<|LOC_787|>", "<|LOC_788|>", "<|LOC_789|>", "<|LOC_790|>", "<|LOC_791|>", "<|LOC_792|>", "<|LOC_793|>", "<|LOC_794|>", "<|LOC_795|>", "<|LOC_796|>", "<|LOC_797|>", "<|LOC_798|>", "<|LOC_799|>", "<|LOC_800|>", "<|LOC_801|>", "<|LOC_802|>", "<|LOC_803|>", "<|LOC_804|>", "<|LOC_805|>", "<|LOC_806|>", "<|LOC_807|>", "<|LOC_808|>", "<|LOC_809|>", "<|LOC_810|>", "<|LOC_811|>", "<|LOC_812|>", "<|LOC_813|>", "<|LOC_814|>", "<|LOC_815|>", "<|LOC_816|>", "<|LOC_817|>", "<|LOC_818|>", "<|LOC_819|>", "<|LOC_820|>", "<|LOC_821|>", "<|LOC_822|>", "<|LOC_823|>", "<|LOC_824|>", "<|LOC_825|>", "<|LOC_826|>", "<|LOC_827|>", "<|LOC_828|>", "<|LOC_829|>", "<|LOC_830|>", "<|LOC_831|>", "<|LOC_832|>", "<|LOC_833|>", "<|LOC_834|>", "<|LOC_835|>", "<|LOC_836|>", "<|LOC_837|>", "<|LOC_838|>", "<|LOC_839|>", "<|LOC_840|>", "<|LOC_841|>", "<|LOC_842|>", "<|LOC_843|>", "<|LOC_844|>", "<|LOC_845|>", "<|LOC_846|>", "<|LOC_847|>", "<|LOC_848|>", "<|LOC_849|>", "<|LOC_850|>", "<|LOC_851|>", "<|LOC_852|>", "<|LOC_853|>", "<|LOC_854|>", "<|LOC_855|>", "<|LOC_856|>", "<|LOC_857|>", "<|LOC_858|>", "<|LOC_859|>", "<|LOC_860|>", "<|LOC_861|>", "<|LOC_862|>", "<|LOC_863|>", "<|LOC_864|>", "<|LOC_865|>", "<|LOC_866|>", "<|LOC_867|>", "<|LOC_868|>", "<|LOC_869|>", "<|LOC_870|>", "<|LOC_871|>", "<|LOC_872|>", "<|LOC_873|>", "<|LOC_874|>", "<|LOC_875|>", "<|LOC_876|>", "<|LOC_877|>", "<|LOC_878|>", "<|LOC_879|>", "<|LOC_880|>", "<|LOC_881|>", "<|LOC_882|>", "<|LOC_883|>", "<|LOC_884|>", "<|LOC_885|>", "<|LOC_886|>", "<|LOC_887|>", "<|LOC_888|>", "<|LOC_889|>", "<|LOC_890|>", "<|LOC_891|>", "<|LOC_892|>", "<|LOC_893|>", "<|LOC_894|>", "<|LOC_895|>", "<|LOC_896|>", "<|LOC_897|>", "<|LOC_898|>", "<|LOC_899|>", "<|LOC_900|>", "<|LOC_901|>", "<|LOC_902|>", "<|LOC_903|>", "<|LOC_904|>", "<|LOC_905|>", "<|LOC_906|>", "<|LOC_907|>", "<|LOC_908|>", "<|LOC_909|>", "<|LOC_910|>", "<|LOC_911|>", "<|LOC_912|>", "<|LOC_913|>", "<|LOC_914|>", "<|LOC_915|>", "<|LOC_916|>", "<|LOC_917|>", "<|LOC_918|>", "<|LOC_919|>", "<|LOC_920|>", "<|LOC_921|>", "<|LOC_922|>", "<|LOC_923|>", "<|LOC_924|>", "<|LOC_925|>", "<|LOC_926|>", "<|LOC_927|>", "<|LOC_928|>", "<|LOC_929|>", "<|LOC_930|>", "<|LOC_931|>", "<|LOC_932|>", "<|LOC_933|>", "<|LOC_934|>", "<|LOC_935|>", "<|LOC_936|>", "<|LOC_937|>", "<|LOC_938|>", "<|LOC_939|>", "<|LOC_940|>", "<|LOC_941|>", "<|LOC_942|>", "<|LOC_943|>", "<|LOC_944|>", "<|LOC_945|>", "<|LOC_946|>", "<|LOC_947|>", "<|LOC_948|>", "<|LOC_949|>", "<|LOC_950|>", "<|LOC_951|>", "<|LOC_952|>", "<|LOC_953|>", "<|LOC_954|>", "<|LOC_955|>", "<|LOC_956|>", "<|LOC_957|>", "<|LOC_958|>", "<|LOC_959|>", "<|LOC_960|>", "<|LOC_961|>", "<|LOC_962|>", "<|LOC_963|>", "<|LOC_964|>", "<|LOC_965|>", "<|LOC_966|>", "<|LOC_967|>", "<|LOC_968|>", "<|LOC_969|>", "<|LOC_970|>", "<|LOC_971|>", "<|LOC_972|>", "<|LOC_973|>", "<|LOC_974|>", "<|LOC_975|>", "<|LOC_976|>", "<|LOC_977|>", "<|LOC_978|>", "<|LOC_979|>", "<|LOC_980|>", "<|LOC_981|>", "<|LOC_982|>", "<|LOC_983|>", "<|LOC_984|>", "<|LOC_985|>", "<|LOC_986|>", "<|LOC_987|>", "<|LOC_988|>", "<|LOC_989|>", "<|LOC_990|>", "<|LOC_991|>", "<|LOC_992|>", "<|LOC_993|>", "<|LOC_994|>", "<|LOC_995|>", "<|LOC_996|>", "<|LOC_997|>", "<|LOC_998|>", "<|LOC_999|>", "<|LOC_1000|>", "<|LOC_BEGIN|>", "<|LOC_END|>", "<|LOC_SEP|>", "<|CROP_COL_SEP|>", "<|CROP_ROW_SEP|>", "<|IMAGE_SEP|>"]}
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ef7db83df785924fb83d7b887b6e822a031c56e15cff40aaf9b982988180df
3
+ size 1614363
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<unk>",
5
+ "unk_token": "<unk>",
6
+ "cls_token": "<|begin_of_sentence|>",
7
+ "sep_token": "<|end_of_sentence|>",
8
+ "mask_token": "<mask:1>",
9
+ "sys_start_token": "<mask:4>",
10
+ "sys_end_token": "<mask:5>",
11
+ "header_start_token": "<mask:6>",
12
+ "header_end_token": "<mask:7>",
13
+ "additional_special_tokens": null,
14
+ "chat_template": "{%- if not add_generation_prompt is defined -%}\n {%- set add_generation_prompt = true -%}\n{%- endif -%}\n{%- if not cls_token is defined -%}\n {%- set cls_token = \"<|begin_of_sentence|>\" -%}\n{%- endif -%}\n{%- if not sep_token is defined -%}\n {%- set sep_token = \"<|end_of_sentence|>\" -%}\n{%- endif -%}\n{{- cls_token -}}\n{%- for message in messages -%}\n {%- if message[\"role\"] == \"user\" -%}\n {{- \"User: \" + message[\"content\"] + \"\n\" -}}\n {%- elif message[\"role\"] == \"assistant\" -%}\n {{- \"Assistant: \" + message[\"content\"] + sep_token -}}\n {%- elif message[\"role\"] == \"system\" -%}\n {{- message[\"content\"] + \"\n\" -}}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- \"Assistant: \" -}}\n{%- endif -%}",
15
+ "tokenizer_class": "Ernie4_5_Tokenizer"
16
+ }