generated from xuyuqing/ailab
add code_geex_2
This commit is contained in:
mjchen6
parent
ba751ee610
commit
9b36dfd4bb
|
|
@ -0,0 +1 @@
|
|||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
|
|
@ -0,0 +1,201 @@
|
|||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright Zhengxiao Du
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
The CodeGeeX License
|
||||
|
||||
1. Definitions
|
||||
|
||||
“Licensor” means the CodeGeeX Model Team that distributes its Software.
|
||||
|
||||
“Software” means the CodeGeeX model parameters made available under this license.
|
||||
|
||||
2. License Grant
|
||||
|
||||
Subject to the terms and conditions of this License, the Licensor hereby grants to you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty-free copyright license to use the Software solely for your non-commercial research purposes.
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
|
||||
|
||||
3. Restriction
|
||||
|
||||
You will not use, copy, modify, merge, publish, distribute, reproduce, or create derivative works of the Software, in whole or in part, for any commercial, military, or illegal purposes.
|
||||
|
||||
You will not use the Software for any act that may undermine China's national security and national unity, harm the public interest of society, or infringe upon the rights and interests of human beings.
|
||||
|
||||
4. Disclaimer
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
||||
5. Limitation of Liability
|
||||
|
||||
EXCEPT TO THE EXTENT PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER BASED IN TORT, NEGLIGENCE, CONTRACT, LIABILITY, OR OTHERWISE WILL ANY LICENSOR BE LIABLE TO YOU FOR ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES, OR ANY OTHER COMMERCIAL LOSSES, EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
|
||||
|
||||
6. Dispute Resolution
|
||||
|
||||
This license shall be governed and construed in accordance with the laws of People’s Republic of China. Any dispute arising from or in connection with this License shall be submitted to Haidian District People's Court in Beijing.
|
||||
|
||||
Note that the license is subject to update to a more comprehensive version. For any questions related to the license and copyright, please contact us at report@aminer.cn.
|
||||
102
README.md
102
README.md
|
|
@ -0,0 +1,102 @@
|
|||
---
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
tags:
|
||||
- codegeex
|
||||
- glm
|
||||
- chatglm
|
||||
- thudm
|
||||
---
|
||||
|
||||
|
||||
|
||||
<p align="center">
|
||||
🏠 <a href="https://codegeex.cn" target="_blank">Homepage</a>｜💻 <a href="https://github.com/THUDM/CodeGeeX2" target="_blank">GitHub</a>｜🛠 Tools <a href="https://marketplace.visualstudio.com/items?itemName=aminer.codegeex" target="_blank">VS Code</a>, <a href="https://plugins.jetbrains.com/plugin/20587-codegeex" target="_blank">Jetbrains</a>｜🤗 <a href="https://huggingface.co/THUDM/codegeex2-6b" target="_blank">HF Repo</a>｜📄 <a href="https://arxiv.org/abs/2303.17568" target="_blank">Paper</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
👋 Join our <a href="https://discord.gg/8gjHdkmAN6" target="_blank">Discord</a>, <a href="https://join.slack.com/t/codegeexworkspace/shared_invite/zt-1s118ffrp-mpKKhQD0tKBmzNZVCyEZLw" target="_blank">Slack</a>, <a href="https://t.me/+IipIayJ32B1jOTg1" target="_blank">Telegram</a>, <a href="https://github.com/THUDM/CodeGeeX2/blob/main/resources/wechat.md"target="_blank">WeChat</a>
|
||||
</p>
|
||||
|
||||
INT4量化版本｜INT4 quantized version [codegeex2-6b-int4](https://huggingface.co/THUDM/codegeex2-6b-int4)
|
||||
|
||||
# CodeGeeX2: 更强大的多语言代码生成模型
|
||||
# A More Powerful Multilingual Code Generation Model
|
||||
|
||||
CodeGeeX2 是多语言代码生成模型 [CodeGeeX](https://github.com/THUDM/CodeGeeX) ([KDD’23](https://arxiv.org/abs/2303.17568)) 的第二代模型。CodeGeeX2 基于 [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B) 架构加入代码预训练实现，得益于 ChatGLM2 的更优性能，CodeGeeX2 在多项指标上取得性能提升（+107% > CodeGeeX；仅60亿参数即超过150亿参数的 StarCoder-15B 近10%），更多特性包括：
|
||||
|
||||
* **更强大的代码能力**：基于 ChatGLM2-6B 基座语言模型，CodeGeeX2-6B 进一步经过了 600B 代码数据预训练，相比一代模型，在代码能力上全面提升，[HumanEval-X](https://huggingface.co/datasets/THUDM/humaneval-x) 评测集的六种编程语言均大幅提升 (Python +57%, C++ +71%, Java +54%, JavaScript +83%, Go +56%, Rust +321\%)，在Python上达到 35.9\% 的 Pass@1 一次通过率，超越规模更大的 StarCoder-15B。
|
||||
* **更优秀的模型特性**：继承 ChatGLM2-6B 模型特性，CodeGeeX2-6B 更好支持中英文输入，支持最大 8192 序列长度，推理速度较一代 CodeGeeX-13B 大幅提升，量化后仅需6GB显存即可运行，支持轻量级本地化部署。
|
||||
* **更全面的AI编程助手**：CodeGeeX插件（[VS Code](https://marketplace.visualstudio.com/items?itemName=aminer.codegeex), [Jetbrains](https://plugins.jetbrains.com/plugin/20587-codegeex)）后端升级，支持超过100种编程语言，新增上下文补全、跨文件补全等实用功能。结合 Ask CodeGeeX 交互式AI编程助手，支持中英文对话解决各种编程问题，包括且不限于代码解释、代码翻译、代码纠错、文档生成等，帮助程序员更高效开发。
|
||||
* **更开放的协议**：CodeGeeX2-6B 权重对学术研究完全开放，填写[登记表](https://open.bigmodel.cn/mla/form?mcode=CodeGeeX2-6B)申请商业使用。
|
||||
|
||||
|
||||
CodeGeeX2 is the second-generation model of the multilingual code generation model [CodeGeeX](https://github.com/THUDM/CodeGeeX) ([KDD’23](https://arxiv.org/abs/2303.17568)), which is implemented based on the [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B) architecture trained on more code data. Due to the advantage of ChatGLM2, CodeGeeX2 has been comprehensively improved in coding capability (+107% > CodeGeeX; with only 6B parameters, surpassing larger StarCoder-15B for some tasks). It has the following features:
|
||||
|
||||
* **More Powerful Coding Capabilities**: Based on the ChatGLM2-6B model, CodeGeeX2-6B has been further pre-trained on 600B code tokens, which has been comprehensively improved in coding capability compared to the first-generation. On the [HumanEval-X](https://huggingface.co/datasets/THUDM/humaneval-x) benchmark, all six languages have been significantly improved (Python +57%, C++ +71%, Java +54%, JavaScript +83%, Go +56%, Rust +321\%), and in Python it reached 35.9% of Pass@1 one-time pass rate, surpassing the larger StarCoder-15B.
|
||||
* **More Useful Features**: Inheriting the ChatGLM2-6B model features, CodeGeeX2-6B better supports both Chinese and English prompts, maximum 8192 sequence length, and the inference speed is significantly improved compared to the first-generation. After quantization, it only needs 6GB of GPU memory for inference, thus supports lightweight local deployment.
|
||||
* **Comprehensive AI Coding Assistant**: The backend of CodeGeeX plugin ([VS Code](https://marketplace.visualstudio.com/items?itemName=aminer.codegeex), [Jetbrains](https://plugins.jetbrains.com/plugin/20587-codegeex)) is upgraded, supporting 100+ programming languages, and adding practical functions such as infilling and cross-file completion. Combined with the "Ask CodeGeeX" interactive AI coding assistant, it can be used to solve various programming problems via Chinese or English dialogue, including but not limited to code summarization, code translation, debugging, and comment generation, which helps increasing the efficiency of developpers.
|
||||
* **Open Liscense**: CodeGeeX2-6B weights are fully open to academic research, and please apply for commercial use by filling in the [registration form](https://open.bigmodel.cn/mla/form?mcode=CodeGeeX2-6B).
|
||||
|
||||
|
||||
## 软件依赖 ｜ Dependency
|
||||
|
||||
```shell
|
||||
pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate
|
||||
```
|
||||
|
||||
## 快速开始 ｜ Get Started
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModel
|
||||
tokenizer = AutoTokenizer.from_pretrained("THUDM/codegeex2-6b", trust_remote_code=True)
|
||||
model = AutoModel.from_pretrained("THUDM/codegeex2-6b", trust_remote_code=True, device='cuda')
|
||||
model = model.eval()
|
||||
|
||||
# remember adding a language tag for better performance
|
||||
prompt = "# language: Python\n# write a bubble sort function\n"
|
||||
inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(inputs, max_length=256, top_k=1)
|
||||
response = tokenizer.decode(outputs[0])
|
||||
|
||||
>>> print(response)
|
||||
# language: Python
|
||||
# write a bubble sort function
|
||||
|
||||
|
||||
def bubble_sort(list):
|
||||
for i in range(len(list) - 1):
|
||||
for j in range(len(list) - 1):
|
||||
if list[j] > list[j + 1]:
|
||||
list[j], list[j + 1] = list[j + 1], list[j]
|
||||
return list
|
||||
|
||||
|
||||
print(bubble_sort([5, 2, 1, 8, 4]))
|
||||
```
|
||||
|
||||
关于更多的使用说明，请参考 CodeGeeX2 的 [Github Repo](https://github.com/THUDM/CodeGeeX2)。
|
||||
|
||||
For more information, please refer to CodeGeeX2's [Github Repo](https://github.com/THUDM/CodeGeeX2).
|
||||
|
||||
## 协议 ｜ License
|
||||
|
||||
本仓库的代码依照 [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) 协议开源，模型的权重的使用则需要遵循 [Model License](MODEL_LICENSE)。
|
||||
|
||||
The code in this repository is open source under the [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) license. The model weights are licensed under the [Model License](MODEL_LICENSE).
|
||||
|
||||
## 引用 ｜ Citation
|
||||
|
||||
如果觉得我们的工作有帮助，欢迎引用以下论文：
|
||||
|
||||
If you find our work helpful, please feel free to cite the following paper:
|
||||
|
||||
```
|
||||
@inproceedings{zheng2023codegeex,
|
||||
title={CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X},
|
||||
author={Qinkai Zheng and Xiao Xia and Xu Zou and Yuxiao Dong and Shan Wang and Yufei Xue and Zihan Wang and Lei Shen and Andi Wang and Yang Li and Teng Su and Zhilin Yang and Jie Tang},
|
||||
booktitle={KDD},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
{
|
||||
"_name_or_path": "THUDM/codegeex2-6b",
|
||||
"model_type": "chatglm",
|
||||
"architectures": [
|
||||
"ChatGLMModel"
|
||||
],
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
|
||||
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
||||
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
||||
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
|
||||
},
|
||||
"add_bias_linear": false,
|
||||
"add_qkv_bias": true,
|
||||
"apply_query_key_layer_scaling": true,
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attention_softmax_in_fp32": true,
|
||||
"bias_dropout_fusion": true,
|
||||
"ffn_hidden_size": 13696,
|
||||
"fp32_residual_connection": false,
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4096,
|
||||
"interleaved_qkv": false,
|
||||
"kv_channels": 128,
|
||||
"layernorm_epsilon": 1e-05,
|
||||
"multi_query_attention": true,
|
||||
"multi_query_group_num": 2,
|
||||
"num_attention_heads": 32,
|
||||
"num_layers": 28,
|
||||
"original_rope": true,
|
||||
"padded_vocab_size": 65024,
|
||||
"post_layer_norm": true,
|
||||
"rmsnorm": true,
|
||||
"rotary_percent": 0.5,
|
||||
"seq_length": 8192,
|
||||
"use_cache": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.30.2",
|
||||
"tie_word_embeddings": false,
|
||||
"eos_token_id": 2
|
||||
}
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
from transformers import PretrainedConfig
|
||||
|
||||
|
||||
class ChatGLMConfig(PretrainedConfig):
|
||||
model_type = "chatglm"
|
||||
def __init__(
|
||||
self,
|
||||
num_layers=28,
|
||||
padded_vocab_size=65024,
|
||||
hidden_size=4096,
|
||||
ffn_hidden_size=13696,
|
||||
kv_channels=128,
|
||||
num_attention_heads=32,
|
||||
seq_length=2048,
|
||||
hidden_dropout=0.0,
|
||||
attention_dropout=0.0,
|
||||
layernorm_epsilon=1e-5,
|
||||
rmsnorm=True,
|
||||
apply_residual_connection_post_layernorm=False,
|
||||
post_layer_norm=True,
|
||||
add_bias_linear=False,
|
||||
add_qkv_bias=False,
|
||||
bias_dropout_fusion=True,
|
||||
multi_query_attention=False,
|
||||
multi_query_group_num=1,
|
||||
apply_query_key_layer_scaling=True,
|
||||
attention_softmax_in_fp32=True,
|
||||
fp32_residual_connection=False,
|
||||
quantization_bit=0,
|
||||
pre_seq_len=None,
|
||||
prefix_projection=False,
|
||||
**kwargs
|
||||
):
|
||||
self.num_layers = num_layers
|
||||
self.vocab_size = padded_vocab_size
|
||||
self.padded_vocab_size = padded_vocab_size
|
||||
self.hidden_size = hidden_size
|
||||
self.ffn_hidden_size = ffn_hidden_size
|
||||
self.kv_channels = kv_channels
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.seq_length = seq_length
|
||||
self.hidden_dropout = hidden_dropout
|
||||
self.attention_dropout = attention_dropout
|
||||
self.layernorm_epsilon = layernorm_epsilon
|
||||
self.rmsnorm = rmsnorm
|
||||
self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
|
||||
self.post_layer_norm = post_layer_norm
|
||||
self.add_bias_linear = add_bias_linear
|
||||
self.add_qkv_bias = add_qkv_bias
|
||||
self.bias_dropout_fusion = bias_dropout_fusion
|
||||
self.multi_query_attention = multi_query_attention
|
||||
self.multi_query_group_num = multi_query_group_num
|
||||
self.apply_query_key_layer_scaling = apply_query_key_layer_scaling
|
||||
self.attention_softmax_in_fp32 = attention_softmax_in_fp32
|
||||
self.fp32_residual_connection = fp32_residual_connection
|
||||
self.quantization_bit = quantization_bit
|
||||
self.pre_seq_len = pre_seq_len
|
||||
self.prefix_projection = prefix_projection
|
||||
super().__init__(**kwargs)
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
{
|
||||
"_from_model_config": true,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.30.2"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,207 @@
|
|||
{
|
||||
"metadata": {
|
||||
"total_size": 12487168064
|
||||
},
|
||||
"weight_map": {
|
||||
"transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.final_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"transformer.output_layer.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00007.bin"
|
||||
}
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
Binary file not shown.
|
After Width: | Height: | Size: 415 KiB |
|
|
@ -0,0 +1,4 @@
|
|||
from transformers import AutoModel
|
||||
|
||||
model = AutoModel.from_pretrained("/mnt/vepfs/qinkai/release/codegeex2-6b/", trust_remote_code=True).cuda()
|
||||
model.save_pretrained("./", max_shard_size="2000MB")
|
||||
|
|
@ -0,0 +1,264 @@
|
|||
import os
|
||||
import torch
|
||||
from typing import List, Optional, Union, Dict
|
||||
from sentencepiece import SentencePieceProcessor
|
||||
from transformers import PreTrainedTokenizer
|
||||
from transformers.utils import logging, PaddingStrategy
|
||||
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
||||
|
||||
|
||||
class SPTokenizer:
|
||||
def __init__(self, model_path: str):
|
||||
# reload tokenizer
|
||||
assert os.path.isfile(model_path), model_path
|
||||
self.sp_model = SentencePieceProcessor(model_file=model_path)
|
||||
|
||||
# BOS / EOS token IDs
|
||||
self.n_words: int = self.sp_model.vocab_size()
|
||||
self.bos_id: int = self.sp_model.bos_id()
|
||||
self.eos_id: int = self.sp_model.eos_id()
|
||||
self.pad_id: int = self.sp_model.unk_id()
|
||||
assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
|
||||
|
||||
special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"]
|
||||
self.special_tokens = {}
|
||||
self.index_special_tokens = {}
|
||||
for token in special_tokens:
|
||||
self.special_tokens[token] = self.n_words
|
||||
self.index_special_tokens[self.n_words] = token
|
||||
self.n_words += 1
|
||||
|
||||
def tokenize(self, s: str):
|
||||
return self.sp_model.EncodeAsPieces(s)
|
||||
|
||||
def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
|
||||
assert type(s) is str
|
||||
t = self.sp_model.encode(s)
|
||||
if bos:
|
||||
t = [self.bos_id] + t
|
||||
if eos:
|
||||
t = t + [self.eos_id]
|
||||
return t
|
||||
|
||||
def decode(self, t: List[int]) -> str:
|
||||
return self.sp_model.decode(t)
|
||||
|
||||
def decode_tokens(self, tokens: List[str]) -> str:
|
||||
text = self.sp_model.DecodePieces(tokens)
|
||||
return text
|
||||
|
||||
def convert_token_to_id(self, token):
|
||||
""" Converts a token (str) in an id using the vocab. """
|
||||
if token in self.special_tokens:
|
||||
return self.special_tokens[token]
|
||||
return self.sp_model.PieceToId(token)
|
||||
|
||||
def convert_id_to_token(self, index):
|
||||
"""Converts an index (integer) in a token (str) using the vocab."""
|
||||
if index in self.index_special_tokens or index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
|
||||
return ""
|
||||
return self.sp_model.IdToPiece(index)
|
||||
|
||||
|
||||
class ChatGLMTokenizer(PreTrainedTokenizer):
|
||||
vocab_files_names = {"vocab_file": "tokenizer.model"}
|
||||
|
||||
model_input_names = ["input_ids", "attention_mask", "position_ids"]
|
||||
|
||||
def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, **kwargs):
|
||||
super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces, **kwargs)
|
||||
self.name = "GLMTokenizer"
|
||||
|
||||
self.vocab_file = vocab_file
|
||||
self.tokenizer = SPTokenizer(vocab_file)
|
||||
self.special_tokens = {
|
||||
"<bos>": self.tokenizer.bos_id,
|
||||
"<eos>": self.tokenizer.eos_id,
|
||||
"<pad>": self.tokenizer.pad_id
|
||||
}
|
||||
|
||||
def get_command(self, token):
|
||||
if token in self.special_tokens:
|
||||
return self.special_tokens[token]
|
||||
assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
|
||||
return self.tokenizer.special_tokens[token]
|
||||
|
||||
@property
|
||||
def unk_token(self) -> str:
|
||||
return "<unk>"
|
||||
|
||||
@property
|
||||
def pad_token(self) -> str:
|
||||
return "<unk>"
|
||||
|
||||
@property
|
||||
def pad_token_id(self):
|
||||
return self.get_command("<pad>")
|
||||
|
||||
@property
|
||||
def eos_token(self) -> str:
|
||||
return "</s>"
|
||||
|
||||
@property
|
||||
def eos_token_id(self):
|
||||
return self.get_command("<eos>")
|
||||
|
||||
@property
|
||||
def vocab_size(self):
|
||||
return self.tokenizer.n_words
|
||||
|
||||
def get_vocab(self):
|
||||
""" Returns vocab as a dict """
|
||||
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
||||
vocab.update(self.added_tokens_encoder)
|
||||
return vocab
|
||||
|
||||
def _tokenize(self, text, **kwargs):
|
||||
return self.tokenizer.tokenize(text)
|
||||
|
||||
def _convert_token_to_id(self, token):
|
||||
""" Converts a token (str) in an id using the vocab. """
|
||||
return self.tokenizer.convert_token_to_id(token)
|
||||
|
||||
def _convert_id_to_token(self, index):
|
||||
"""Converts an index (integer) in a token (str) using the vocab."""
|
||||
return self.tokenizer.convert_id_to_token(index)
|
||||
|
||||
def convert_tokens_to_string(self, tokens: List[str]) -> str:
|
||||
return self.tokenizer.decode_tokens(tokens)
|
||||
|
||||
def save_vocabulary(self, save_directory, filename_prefix=None):
|
||||
"""
|
||||
Save the vocabulary and special tokens file to a directory.
|
||||
|
||||
Args:
|
||||
save_directory (`str`):
|
||||
The directory in which to save the vocabulary.
|
||||
filename_prefix (`str`, *optional*):
|
||||
An optional prefix to add to the named of the saved files.
|
||||
|
||||
Returns:
|
||||
`Tuple(str)`: Paths to the files saved.
|
||||
"""
|
||||
if os.path.isdir(save_directory):
|
||||
vocab_file = os.path.join(
|
||||
save_directory, self.vocab_files_names["vocab_file"]
|
||||
)
|
||||
else:
|
||||
vocab_file = save_directory
|
||||
|
||||
with open(self.vocab_file, 'rb') as fin:
|
||||
proto_str = fin.read()
|
||||
|
||||
with open(vocab_file, "wb") as writer:
|
||||
writer.write(proto_str)
|
||||
|
||||
return (vocab_file,)
|
||||
|
||||
def get_prefix_tokens(self):
|
||||
prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
|
||||
return prefix_tokens
|
||||
|
||||
def build_prompt(self, query, history=None):
|
||||
if history is None:
|
||||
history = []
|
||||
prompt = ""
|
||||
for i, (old_query, response) in enumerate(history):
|
||||
prompt += "[Round {}]\n\n问：{}\n\n答：{}\n\n".format(i + 1, old_query, response)
|
||||
prompt += "[Round {}]\n\n问：{}\n\n答：".format(len(history) + 1, query)
|
||||
return prompt
|
||||
|
||||
def build_inputs_with_special_tokens(
|
||||
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
||||
) -> List[int]:
|
||||
"""
|
||||
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
||||
adding special tokens. A BERT sequence has the following format:
|
||||
|
||||
- single sequence: `[CLS] X [SEP]`
|
||||
- pair of sequences: `[CLS] A [SEP] B [SEP]`
|
||||
|
||||
Args:
|
||||
token_ids_0 (`List[int]`):
|
||||
List of IDs to which the special tokens will be added.
|
||||
token_ids_1 (`List[int]`, *optional*):
|
||||
Optional second list of IDs for sequence pairs.
|
||||
|
||||
Returns:
|
||||
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
||||
"""
|
||||
prefix_tokens = self.get_prefix_tokens()
|
||||
token_ids_0 = prefix_tokens + token_ids_0
|
||||
if token_ids_1 is not None:
|
||||
token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
|
||||
return token_ids_0
|
||||
|
||||
def _pad(
|
||||
self,
|
||||
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
||||
max_length: Optional[int] = None,
|
||||
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
||||
pad_to_multiple_of: Optional[int] = None,
|
||||
return_attention_mask: Optional[bool] = None,
|
||||
) -> dict:
|
||||
"""
|
||||
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
|
||||
|
||||
Args:
|
||||
encoded_inputs:
|
||||
Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
|
||||
max_length: maximum length of the returned list and optionally padding length (see below).
|
||||
Will truncate by taking into account the special tokens.
|
||||
padding_strategy: PaddingStrategy to use for padding.
|
||||
|
||||
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
|
||||
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
|
||||
- PaddingStrategy.DO_NOT_PAD: Do not pad
|
||||
The tokenizer padding sides are defined in self.padding_side:
|
||||
|
||||
- 'left': pads on the left of the sequences
|
||||
- 'right': pads on the right of the sequences
|
||||
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
|
||||
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
|
||||
`>= 7.5` (Volta).
|
||||
return_attention_mask:
|
||||
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
||||
"""
|
||||
# Load from model defaults
|
||||
# assert self.padding_side == "left"
|
||||
|
||||
required_input = encoded_inputs[self.model_input_names[0]]
|
||||
seq_length = len(required_input)
|
||||
|
||||
if padding_strategy == PaddingStrategy.LONGEST:
|
||||
max_length = len(required_input)
|
||||
|
||||
if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
|
||||
max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
|
||||
|
||||
needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
|
||||
|
||||
# Initialize attention mask if not present.
|
||||
if "attention_mask" not in encoded_inputs:
|
||||
encoded_inputs["attention_mask"] = [1] * seq_length
|
||||
|
||||
if "position_ids" not in encoded_inputs:
|
||||
encoded_inputs["position_ids"] = list(range(seq_length))
|
||||
|
||||
if needs_to_be_padded:
|
||||
difference = max_length - len(required_input)
|
||||
|
||||
if self.padding_side == "left":
|
||||
if "attention_mask" in encoded_inputs:
|
||||
encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
|
||||
if "position_ids" in encoded_inputs:
|
||||
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
||||
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
||||
else:
|
||||
if "attention_mask" in encoded_inputs:
|
||||
encoded_inputs["attention_mask"] = encoded_inputs["attention_mask"] + [0] * difference
|
||||
if "position_ids" in encoded_inputs:
|
||||
encoded_inputs["position_ids"] = encoded_inputs["position_ids"] + [0] * difference
|
||||
encoded_inputs[self.model_input_names[0]] = required_input + [self.pad_token_id] * difference
|
||||
|
||||
return encoded_inputs
|
||||
Binary file not shown.
|
|
@ -0,0 +1,12 @@
|
|||
{
|
||||
"name_or_path": "THUDM/codegeex2-6b",
|
||||
"remove_space": false,
|
||||
"do_lower_case": false,
|
||||
"tokenizer_class": "ChatGLMTokenizer",
|
||||
"auto_map": {
|
||||
"AutoTokenizer": [
|
||||
"tokenization_chatglm.ChatGLMTokenizer",
|
||||
null
|
||||
]
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue