Upload README.md with huggingface_hub
This commit is contained in:
ai-modelscope
31
.gitattributes
vendored
31
.gitattributes
vendored
@@ -1,47 +1,36 @@
|
|||||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
*.model filter=lfs diff=lfs merge=lfs -text
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|||||||
201
LICENSE
Normal file
201
LICENSE
Normal file
@@ -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 [yyyy] [name of copyright owner]
|
||||||
|
|
||||||
|
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.
|
||||||
450
README.md
450
README.md
@@ -1,47 +1,417 @@
|
|||||||
---
|
---
|
||||||
license: Apache License 2.0
|
tags:
|
||||||
|
- code
|
||||||
#model-type:
|
base_model:
|
||||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
- TechxGenus/CursorCore-Yi-1.5B-LC
|
||||||
#- gpt
|
library_name: transformers
|
||||||
|
pipeline_tag: text-generation
|
||||||
#domain:
|
license: apache-2.0
|
||||||
##如 nlp、cv、audio、multi-modal
|
|
||||||
#- nlp
|
|
||||||
|
|
||||||
#language:
|
|
||||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
|
||||||
#- cn
|
|
||||||
|
|
||||||
#metrics:
|
|
||||||
##如 CIDEr、Blue、ROUGE 等
|
|
||||||
#- CIDEr
|
|
||||||
|
|
||||||
#tags:
|
|
||||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
|
||||||
#- pretrained
|
|
||||||
|
|
||||||
#tools:
|
|
||||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
|
||||||
#- vllm
|
|
||||||
---
|
---
|
||||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
|
||||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
|
||||||
|
|
||||||
SDK下载
|
# CursorCore: Assist Programming through Aligning Anything
|
||||||
```bash
|
|
||||||
#安装ModelScope
|
<p align="center">
|
||||||
pip install modelscope
|
<a href="http://arxiv.org/abs/2410.07002">[📄arXiv]</a> |
|
||||||
```
|
<a href="https://hf.co/papers/2410.07002">[🤗HF Paper]</a> |
|
||||||
|
<a href="https://huggingface.co/collections/TechxGenus/cursorcore-series-6706618c38598468866b60e2">[🤖Models]</a> |
|
||||||
|
<a href="https://github.com/TechxGenus/CursorCore">[🛠️Code]</a> |
|
||||||
|
<a href="https://github.com/TechxGenus/CursorWeb">[Web]</a> |
|
||||||
|
<a href="https://discord.gg/Z5Tev8fV">[Discord]</a>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
<hr>
|
||||||
|
|
||||||
|
- [CursorCore: Assist Programming through Aligning Anything](#cursorcore-assist-programming-through-aligning-anything)
|
||||||
|
- [Introduction](#introduction)
|
||||||
|
- [Models](#models)
|
||||||
|
- [Usage](#usage)
|
||||||
|
- [1) Normal chat](#1-normal-chat)
|
||||||
|
- [2) Assistant-Conversation](#2-assistant-conversation)
|
||||||
|
- [3) Web Demo](#3-web-demo)
|
||||||
|
- [Future Work](#future-work)
|
||||||
|
- [Citation](#citation)
|
||||||
|
- [Contribution](#contribution)
|
||||||
|
|
||||||
|
<hr>
|
||||||
|
|
||||||
|
## Introduction
|
||||||
|
|
||||||
|
CursorCore is a series of open-source models designed for AI-assisted programming. It aims to support features such as automated editing and inline chat, replicating the core abilities of closed-source AI-assisted programming tools like Cursor. This is achieved by aligning data generated through Programming-Instruct. Please read [our paper](http://arxiv.org/abs/2410.07002) to learn more.
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
<img width="100%" alt="conversation" src="https://raw.githubusercontent.com/TechxGenus/CursorCore/main/pictures/conversation.png">
|
||||||
|
</p>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Models
|
||||||
|
|
||||||
|
Our models have been open-sourced on Hugging Face. You can access our models here: [CursorCore-Series](https://huggingface.co/collections/TechxGenus/cursorcore-series-6706618c38598468866b60e2"). We also provide pre-quantized weights for GPTQ and AWQ here: [CursorCore-Quantization](https://huggingface.co/collections/TechxGenus/cursorcore-quantization-67066431f29f252494ee8cf3)
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
Here are some examples of how to use our model:
|
||||||
|
|
||||||
|
### 1) Normal chat
|
||||||
|
|
||||||
|
Script:
|
||||||
|
|
||||||
|
````python
|
||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-9B")
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"TechxGenus/CursorCore-Yi-9B",
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{"role": "user", "content": "Hi!"},
|
||||||
|
]
|
||||||
|
prompt = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=False,
|
||||||
|
add_generation_prompt=True
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = tokenizer.encode(prompt, return_tensors="pt")
|
||||||
|
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512)
|
||||||
|
print(tokenizer.decode(outputs[0]))
|
||||||
|
````
|
||||||
|
|
||||||
|
Output:
|
||||||
|
|
||||||
|
````txt
|
||||||
|
<|im_start|>system
|
||||||
|
You are a helpful programming assistant.<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
Hi!<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
Hello! I'm an AI language model and I can help you with any programming questions you might have. What specific problem or task are you trying to solve?<|im_end|>
|
||||||
|
````
|
||||||
|
|
||||||
|
### 2) Assistant-Conversation
|
||||||
|
|
||||||
|
In our work, we introduce a new framework of AI-assisted programming task. It is designed for aligning anything during programming process, used for the implementation of features like Tab and Inline Chat.
|
||||||
|
|
||||||
|
Script 1:
|
||||||
|
|
||||||
|
````python
|
||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
from eval.utils import prepare_input_for_wf
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-9B")
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"TechxGenus/CursorCore-Yi-9B",
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
sample = {
|
||||||
|
"history": [
|
||||||
|
{
|
||||||
|
"type": "code",
|
||||||
|
"lang": "python",
|
||||||
|
"code": """def quick_sort(arr):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)"""
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"current": {
|
||||||
|
"type": "code",
|
||||||
|
"lang": "python",
|
||||||
|
"code": """def quick_sort(array):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)"""
|
||||||
|
},
|
||||||
|
"user": ""
|
||||||
|
}
|
||||||
|
|
||||||
|
prompt = tokenizer.apply_chat_template(
|
||||||
|
prepare_input_for_wf(sample),
|
||||||
|
tokenize=False,
|
||||||
|
chat_template="assistant-conversation",
|
||||||
|
add_generation_prompt=True
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = tokenizer.encode(prompt, return_tensors="pt")
|
||||||
|
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512, do_sample=False)
|
||||||
|
print(tokenizer.decode(outputs[0]))
|
||||||
|
````
|
||||||
|
|
||||||
|
Output 1:
|
||||||
|
|
||||||
|
````txt
|
||||||
|
<|im_start|>system
|
||||||
|
You are a helpful programming assistant.<|im_end|>
|
||||||
|
<|im_start|>history
|
||||||
```python
|
```python
|
||||||
#SDK模型下载
|
def quick_sort(arr):
|
||||||
from modelscope import snapshot_download
|
if len(arr) <= 1:
|
||||||
model_dir = snapshot_download('TechxGenus-MS/CursorCore-Yi-1.5B-LC-AWQ')
|
return arr
|
||||||
|
pivot = arr[len(arr) // 2]
|
||||||
|
left = [x for x in arr if x < pivot]
|
||||||
|
middle = [x for x in arr if x == pivot]
|
||||||
|
right = [x for x in arr if x > pivot]
|
||||||
|
return quick_sort(left) + middle + quick_sort(right)
|
||||||
|
```<|im_end|>
|
||||||
|
<|im_start|>current
|
||||||
|
```python
|
||||||
|
def quick_sort(array):
|
||||||
|
if len(arr) <= 1:
|
||||||
|
return arr
|
||||||
|
pivot = arr[len(arr) // 2]
|
||||||
|
left = [x for x in arr if x < pivot]
|
||||||
|
middle = [x for x in arr if x == pivot]
|
||||||
|
right = [x for x in arr if x > pivot]
|
||||||
|
return quick_sort(left) + middle + quick_sort(right)
|
||||||
|
```<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
<|next_start|>```python
|
||||||
|
def quick_sort(array):
|
||||||
|
if len(array) <= 1:
|
||||||
|
return array
|
||||||
|
pivot = array[len(array) // 2]
|
||||||
|
left = [x for x in array if x < pivot]
|
||||||
|
middle = [x for x in array if x == pivot]
|
||||||
|
right = [x for x in array if x > pivot]
|
||||||
|
return quick_sort(left) + middle + quick_sort(right)
|
||||||
|
```<|next_end|>
|
||||||
|
The user has provided a revised code change that corrects the parameter name from `arr` to `array` in the `quick_sort` function. This change ensures consistency in the function definition and avoids potential confusion or errors.
|
||||||
|
|
||||||
|
To implement this, we will:
|
||||||
|
1. Update the parameter name in the function definition from `arr` to `array`.
|
||||||
|
2. Ensure that all references to `arr` within the function are updated to `array`.
|
||||||
|
|
||||||
|
This will make the function definition and internal references consistent, improving code readability and maintainability.<|im_end|>
|
||||||
|
````
|
||||||
|
|
||||||
|
Script 2:
|
||||||
|
|
||||||
|
````python
|
||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
from eval.utils import prepare_input_for_wf
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-9B")
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"TechxGenus/CursorCore-Yi-9B",
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
sample = {
|
||||||
|
"history": [],
|
||||||
|
"current": {
|
||||||
|
"type": "code",
|
||||||
|
"lang": "python",
|
||||||
|
"code": """def quick_sort(array):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)"""
|
||||||
|
},
|
||||||
|
"user": "Add Docstring."
|
||||||
|
}
|
||||||
|
|
||||||
|
prompt = tokenizer.apply_chat_template(
|
||||||
|
prepare_input_for_wf(sample),
|
||||||
|
tokenize=False,
|
||||||
|
chat_template="assistant-conversation",
|
||||||
|
add_generation_prompt=True
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = tokenizer.encode(prompt, return_tensors="pt")
|
||||||
|
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512, do_sample=False)
|
||||||
|
print(tokenizer.decode(outputs[0]))
|
||||||
|
````
|
||||||
|
|
||||||
|
Output 2:
|
||||||
|
|
||||||
|
````txt
|
||||||
|
<|im_start|>system
|
||||||
|
You are a helpful programming assistant.<|im_end|>
|
||||||
|
<|im_start|>current
|
||||||
|
```python
|
||||||
|
def quick_sort(array):
|
||||||
|
if len(arr) <= 1:
|
||||||
|
return arr
|
||||||
|
pivot = arr[len(arr) // 2]
|
||||||
|
left = [x for x in arr if x < pivot]
|
||||||
|
middle = [x for x in arr if x == pivot]
|
||||||
|
right = [x for x in arr if x > pivot]
|
||||||
|
return quick_sort(left) + middle + quick_sort(right)
|
||||||
|
```<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
Add Docstring.<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
<|next_start|>```python
|
||||||
|
def quick_sort(array):
|
||||||
|
"""
|
||||||
|
This is an implementation of the quick sort algorithm.
|
||||||
|
"""
|
||||||
|
if len(arr) <= 1:
|
||||||
|
return arr
|
||||||
|
pivot = arr[len(arr) // 2]
|
||||||
|
left = [x for x in arr if x < pivot]
|
||||||
|
middle = [x for x in arr if x == pivot]
|
||||||
|
right = [x for x in arr if x > pivot]
|
||||||
|
return quick_sort(left) + middle + quick_sort(right)
|
||||||
|
```<|next_end|><|im_end|>
|
||||||
|
````
|
||||||
|
|
||||||
|
For models in Locate-and-Change (LC) and Search-and-Replace (SR) formats, the output examples are as follows:
|
||||||
|
|
||||||
|
Script for LC:
|
||||||
|
|
||||||
|
````python
|
||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
from eval.utils import prepare_input_for_lc
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-1.5B-LC")
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"TechxGenus/CursorCore-Yi-1.5B-LC",
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
sample = {
|
||||||
|
"history": [],
|
||||||
|
"current": {
|
||||||
|
"type": "code",
|
||||||
|
"lang": "python",
|
||||||
|
"code": """def quick_sort(array):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)"""
|
||||||
|
},
|
||||||
|
"user": "Add Docstring."
|
||||||
|
}
|
||||||
|
|
||||||
|
prompt = tokenizer.apply_chat_template(
|
||||||
|
prepare_input_for_lc(sample),
|
||||||
|
tokenize=False,
|
||||||
|
chat_template="assistant-conversation",
|
||||||
|
add_generation_prompt=True
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = tokenizer.encode(prompt, return_tensors="pt")
|
||||||
|
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512, do_sample=False)
|
||||||
|
print(tokenizer.decode(outputs[0]))
|
||||||
|
````
|
||||||
|
|
||||||
|
Output for LC:
|
||||||
|
|
||||||
|
````txt
|
||||||
|
<|im_start|>system
|
||||||
|
You are a helpful programming assistant.<|im_end|>
|
||||||
|
<|im_start|>current
|
||||||
|
```python
|
||||||
|
1 def quick_sort(array):
|
||||||
|
2 if len(arr) <= 1:
|
||||||
|
3 return arr
|
||||||
|
4 pivot = arr[len(arr) // 2]
|
||||||
|
5 left = [x for x in arr if x < pivot]
|
||||||
|
6 middle = [x for x in arr if x == pivot]
|
||||||
|
7 right = [x for x in arr if x > pivot]
|
||||||
|
8 return quick_sort(left) + middle + quick_sort(right)
|
||||||
|
```<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
Add Docstring.<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
<|next_start|>1,1
|
||||||
```
|
```
|
||||||
Git下载
|
'''This function will sort an array using quick sort algorithm'''
|
||||||
```
|
```<|next_end|>
|
||||||
#Git模型下载
|
To enhance the readability and maintainability of the code, we should add a docstring to the `quick_sort` function. A docstring provides a clear description of what the function does, which is particularly useful for other developers who might use or modify this code in the future.
|
||||||
git clone https://www.modelscope.cn/TechxGenus-MS/CursorCore-Yi-1.5B-LC-AWQ.git
|
|
||||||
|
The docstring will be added immediately after the function definition, explaining that the function uses the quick sort algorithm to sort an array. This will make the code more self-explanatory and easier to understand.
|
||||||
|
|
||||||
|
Here's the plan:
|
||||||
|
1. Add a docstring at the beginning of the `quick_sort` function.
|
||||||
|
2. Ensure the docstring is clear and concise, describing the purpose of the function.
|
||||||
|
|
||||||
|
This modification will improve the code's documentation without altering its functionality.<|im_end|>
|
||||||
|
````
|
||||||
|
|
||||||
|
Script for SR:
|
||||||
|
|
||||||
|
````python
|
||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
from eval.utils import prepare_input_for_sr
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-1.5B-SR")
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"TechxGenus/CursorCore-Yi-1.5B-SR",
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
sample = {
|
||||||
|
"history": [],
|
||||||
|
"current": {
|
||||||
|
"type": "code",
|
||||||
|
"lang": "python",
|
||||||
|
"code": """def quick_sort(array):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)"""
|
||||||
|
},
|
||||||
|
"user": "Add Docstring."
|
||||||
|
}
|
||||||
|
|
||||||
|
prompt = tokenizer.apply_chat_template(
|
||||||
|
prepare_input_for_sr(sample),
|
||||||
|
tokenize=False,
|
||||||
|
chat_template="assistant-conversation",
|
||||||
|
add_generation_prompt=True
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = tokenizer.encode(prompt, return_tensors="pt")
|
||||||
|
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512, do_sample=False)
|
||||||
|
print(tokenizer.decode(outputs[0]))
|
||||||
|
````
|
||||||
|
|
||||||
|
Output for SR:
|
||||||
|
|
||||||
|
````txt
|
||||||
|
<|im_start|>system
|
||||||
|
You are a helpful programming assistant.<|im_end|>
|
||||||
|
<|im_start|>current
|
||||||
|
```python
|
||||||
|
def quick_sort(array):
|
||||||
|
if len(arr) <= 1:
|
||||||
|
return arr
|
||||||
|
pivot = arr[len(arr) // 2]
|
||||||
|
left = [x for x in arr if x < pivot]
|
||||||
|
middle = [x for x in arr if x == pivot]
|
||||||
|
right = [x for x in arr if x > pivot]
|
||||||
|
return quick_sort(left) + middle + quick_sort(right)
|
||||||
|
```<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
Add Docstring.<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
<|next_start|>```python
|
||||||
|
def quick_sort(array):
|
||||||
|
<|search_and_replace|>
|
||||||
|
def quick_sort(array):
|
||||||
|
"""
|
||||||
|
This function implements quick sort algorithm
|
||||||
|
"""
|
||||||
|
```<|next_end|><|im_end|>
|
||||||
|
````
|
||||||
|
|
||||||
|
### 3) Web Demo
|
||||||
|
|
||||||
|
We create a web demo for CursorCore. Please visit [CursorWeb](https://github.com/TechxGenus/CursorWeb) for more details.
|
||||||
|
|
||||||
|
## Future Work
|
||||||
|
|
||||||
|
CursorCore is still in a very early stage, and lots of work is needed to achieve a better user experience. For example:
|
||||||
|
|
||||||
|
- Repository-level editing support
|
||||||
|
- Better and faster editing formats
|
||||||
|
- Better user interface and presentation
|
||||||
|
- ...
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@article{jiang2024cursorcore,
|
||||||
|
title = {CursorCore: Assist Programming through Aligning Anything},
|
||||||
|
author = {Hao Jiang and Qi Liu and Rui Li and Shengyu Ye and Shijin Wang},
|
||||||
|
year = {2024},
|
||||||
|
journal = {arXiv preprint arXiv: 2410.07002}
|
||||||
|
}
|
||||||
```
|
```
|
||||||
|
|
||||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
## Contribution
|
||||||
|
|
||||||
|
Contributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request.
|
||||||
|
|||||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "TechxGenus/CursorCore-Yi-1.5B-LC",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 7,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 5504,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 24,
|
||||||
|
"num_key_value_heads": 16,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"quantization_config": {
|
||||||
|
"bits": 4,
|
||||||
|
"group_size": 64,
|
||||||
|
"modules_to_not_convert": null,
|
||||||
|
"quant_method": "awq",
|
||||||
|
"version": "gemm",
|
||||||
|
"zero_point": true
|
||||||
|
},
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 10000000,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.45.1",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 64064
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": 7,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.45.1"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:af6f939a75b6287cfbace8399e019a8ea06c695f5858cadd41858ca69d0ed27c
|
||||||
|
size 1179632368
|
||||||
40
special_tokens_map.json
Normal file
40
special_tokens_map.json
Normal file
@@ -0,0 +1,40 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|next_start|>",
|
||||||
|
"<|next_end|>",
|
||||||
|
"<|target_start|>",
|
||||||
|
"<|target_end|>",
|
||||||
|
"<|target|>",
|
||||||
|
"<|search_and_replace|>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|startoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
504293
tokenizer.json
Normal file
504293
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
||||||
|
size 1033105
|
||||||
137
tokenizer_config.json
Normal file
137
tokenizer_config.json
Normal file
@@ -0,0 +1,137 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"add_prefix_space": null,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"0": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"1": {
|
||||||
|
"content": "<|startoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"6": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"7": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"64000": {
|
||||||
|
"content": "<|next_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"64001": {
|
||||||
|
"content": "<|next_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"64002": {
|
||||||
|
"content": "<|target_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"64003": {
|
||||||
|
"content": "<|target_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"64004": {
|
||||||
|
"content": "<|target|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"64005": {
|
||||||
|
"content": "<|search_and_replace|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|next_start|>",
|
||||||
|
"<|next_end|>",
|
||||||
|
"<|target_start|>",
|
||||||
|
"<|target_end|>",
|
||||||
|
"<|target|>",
|
||||||
|
"<|search_and_replace|>"
|
||||||
|
],
|
||||||
|
"bos_token": "<|startoftext|>",
|
||||||
|
"chat_template": [
|
||||||
|
{
|
||||||
|
"name": "default",
|
||||||
|
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "assistant-conversation",
|
||||||
|
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "prefix_response",
|
||||||
|
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] }}{% if not loop.last %}{{ '<|im_end|>' }}{% endif %}{% endfor %}"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"legacy": true,
|
||||||
|
"max_length": 16384,
|
||||||
|
"model_max_length": 16384,
|
||||||
|
"pad_to_multiple_of": null,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"pad_token_type_id": 0,
|
||||||
|
"padding_side": "left",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"spaces_between_special_tokens": false,
|
||||||
|
"stride": 0,
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"truncation_side": "right",
|
||||||
|
"truncation_strategy": "longest_first",
|
||||||
|
"unk_token": "<unk>",
|
||||||
|
"use_default_system_prompt": false
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user