IAAR-Shanghai/xVerify-9B-C
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: IAAR-Shanghai/xVerify-9B-C
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-16 09:06:16 +08:00
commit 8bd8d5bd75
17 changed files with 2492 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin 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
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib 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
*.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
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet 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
*.pth 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
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite 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
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

402
LICENSE Normal file
View File

@@ -0,0 +1,402 @@
Attribution-NonCommercial-NoDerivatives 4.0 International
=======================================================================
Creative Commons Corporation ("Creative Commons") is not a law firm and
does not provide legal services or legal advice. Distribution of
Creative Commons public licenses does not create a lawyer-client or
other relationship. Creative Commons makes its licenses and related
information available on an "as-is" basis. Creative Commons gives no
warranties regarding its licenses, any material licensed under their
terms and conditions, or any related information. Creative Commons
disclaims all liability for damages resulting from their use to the
fullest extent possible.
Using Creative Commons Public Licenses
Creative Commons public licenses provide a standard set of terms and
conditions that creators and other rights holders may use to share
original works of authorship and other material subject to copyright
and certain other rights specified in the public license below. The
following considerations are for informational purposes only, are not
exhaustive, and do not form part of our licenses.
Considerations for licensors: Our public licenses are
intended for use by those authorized to give the public
permission to use material in ways otherwise restricted by
copyright and certain other rights. Our licenses are
irrevocable. Licensors should read and understand the terms
and conditions of the license they choose before applying it.
Licensors should also secure all rights necessary before
applying our licenses so that the public can reuse the
material as expected. Licensors should clearly mark any
material not subject to the license. This includes other CC-
licensed material, or material used under an exception or
limitation to copyright. More considerations for licensors:
wiki.creativecommons.org/Considerations_for_licensors
Considerations for the public: By using one of our public
licenses, a licensor grants the public permission to use the
licensed material under specified terms and conditions. If
the licensor's permission is not necessary for any reason--for
example, because of any applicable exception or limitation to
copyright--then that use is not regulated by the license. Our
licenses grant only permissions under copyright and certain
other rights that a licensor has authority to grant. Use of
the licensed material may still be restricted for other
reasons, including because others have copyright or other
rights in the material. A licensor may make special requests,
such as asking that all changes be marked or described.
Although not required by our licenses, you are encouraged to
respect those requests where reasonable. More considerations
for the public:
wiki.creativecommons.org/Considerations_for_licensees
=======================================================================
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0
International Public License
By exercising the Licensed Rights (defined below), You accept and agree
to be bound by the terms and conditions of this Creative Commons
Attribution-NonCommercial-NoDerivatives 4.0 International Public
License ("Public License"). To the extent this Public License may be
interpreted as a contract, You are granted the Licensed Rights in
consideration of Your acceptance of these terms and conditions, and the
Licensor grants You such rights in consideration of benefits the
Licensor receives from making the Licensed Material available under
these terms and conditions.
Section 1 -- Definitions.
a. Adapted Material means material subject to Copyright and Similar
Rights that is derived from or based upon the Licensed Material
and in which the Licensed Material is translated, altered,
arranged, transformed, or otherwise modified in a manner requiring
permission under the Copyright and Similar Rights held by the
Licensor. For purposes of this Public License, where the Licensed
Material is a musical work, performance, or sound recording,
Adapted Material is always produced where the Licensed Material is
synched in timed relation with a moving image.
b. Copyright and Similar Rights means copyright and/or similar rights
closely related to copyright including, without limitation,
performance, broadcast, sound recording, and Sui Generis Database
Rights, without regard to how the rights are labeled or
categorized. For purposes of this Public License, the rights
specified in Section 2(b)(1)-(2) are not Copyright and Similar
Rights.
c. Effective Technological Measures means those measures that, in the
absence of proper authority, may not be circumvented under laws
fulfilling obligations under Article 11 of the WIPO Copyright
Treaty adopted on December 20, 1996, and/or similar international
agreements.
d. Exceptions and Limitations means fair use, fair dealing, and/or
any other exception or limitation to Copyright and Similar Rights
that applies to Your use of the Licensed Material.
e. Licensed Material means the artistic or literary work, database,
or other material to which the Licensor applied this Public
License.
f. Licensed Rights means the rights granted to You subject to the
terms and conditions of this Public License, which are limited to
all Copyright and Similar Rights that apply to Your use of the
Licensed Material and that the Licensor has authority to license.
g. Licensor means the individual(s) or entity(ies) granting rights
under this Public License.
h. NonCommercial means not primarily intended for or directed towards
commercial advantage or monetary compensation. For purposes of
this Public License, the exchange of the Licensed Material for
other material subject to Copyright and Similar Rights by digital
file-sharing or similar means is NonCommercial provided there is
no payment of monetary compensation in connection with the
exchange.
i. Share means to provide material to the public by any means or
process that requires permission under the Licensed Rights, such
as reproduction, public display, public performance, distribution,
dissemination, communication, or importation, and to make material
available to the public including in ways that members of the
public may access the material from a place and at a time
individually chosen by them.
j. Sui Generis Database Rights means rights other than copyright
resulting from Directive 96/9/EC of the European Parliament and of
the Council of 11 March 1996 on the legal protection of databases,
as amended and/or succeeded, as well as other essentially
equivalent rights anywhere in the world.
k. You means the individual or entity exercising the Licensed Rights
under this Public License. Your has a corresponding meaning.
Section 2 -- Scope.
a. License grant.
1. Subject to the terms and conditions of this Public License,
the Licensor hereby grants You a worldwide, royalty-free,
non-sublicensable, non-exclusive, irrevocable license to
exercise the Licensed Rights in the Licensed Material to:
a. reproduce and Share the Licensed Material, in whole or
in part, for NonCommercial purposes only; and
b. produce and reproduce, but not Share, Adapted Material
for NonCommercial purposes only.
2. Exceptions and Limitations. For the avoidance of doubt, where
Exceptions and Limitations apply to Your use, this Public
License does not apply, and You do not need to comply with
its terms and conditions.
3. Term. The term of this Public License is specified in Section
6(a).
4. Media and formats; technical modifications allowed. The
Licensor authorizes You to exercise the Licensed Rights in
all media and formats whether now known or hereafter created,
and to make technical modifications necessary to do so. The
Licensor waives and/or agrees not to assert any right or
authority to forbid You from making technical modifications
necessary to exercise the Licensed Rights, including
technical modifications necessary to circumvent Effective
Technological Measures. For purposes of this Public License,
simply making modifications authorized by this Section 2(a)
(4) never produces Adapted Material.
5. Downstream recipients.
a. Offer from the Licensor -- Licensed Material. Every
recipient of the Licensed Material automatically
receives an offer from the Licensor to exercise the
Licensed Rights under the terms and conditions of this
Public License.
b. No downstream restrictions. You may not offer or impose
any additional or different terms or conditions on, or
apply any Effective Technological Measures to, the
Licensed Material if doing so restricts exercise of the
Licensed Rights by any recipient of the Licensed
Material.
6. No endorsement. Nothing in this Public License constitutes or
may be construed as permission to assert or imply that You
are, or that Your use of the Licensed Material is, connected
with, or sponsored, endorsed, or granted official status by,
the Licensor or others designated to receive attribution as
provided in Section 3(a)(1)(A)(i).
b. Other rights.
1. Moral rights, such as the right of integrity, are not
licensed under this Public License, nor are publicity,
privacy, and/or other similar personality rights; however, to
the extent possible, the Licensor waives and/or agrees not to
assert any such rights held by the Licensor to the limited
extent necessary to allow You to exercise the Licensed
Rights, but not otherwise.
2. Patent and trademark rights are not licensed under this
Public License.
3. To the extent possible, the Licensor waives any right to
collect royalties from You for the exercise of the Licensed
Rights, whether directly or through a collecting society
under any voluntary or waivable statutory or compulsory
licensing scheme. In all other cases the Licensor expressly
reserves any right to collect such royalties, including when
the Licensed Material is used other than for NonCommercial
purposes.
Section 3 -- License Conditions.
Your exercise of the Licensed Rights is expressly made subject to the
following conditions.
a. Attribution.
1. If You Share the Licensed Material, You must:
a. retain the following if it is supplied by the Licensor
with the Licensed Material:
i. identification of the creator(s) of the Licensed
Material and any others designated to receive
attribution, in any reasonable manner requested by
the Licensor (including by pseudonym if
designated);
ii. a copyright notice;
iii. a notice that refers to this Public License;
iv. a notice that refers to the disclaimer of
warranties;
v. a URI or hyperlink to the Licensed Material to the
extent reasonably practicable;
b. indicate if You modified the Licensed Material and
retain an indication of any previous modifications; and
c. indicate the Licensed Material is licensed under this
Public License, and include the text of, or the URI or
hyperlink to, this Public License.
For the avoidance of doubt, You do not have permission under
this Public License to Share Adapted Material.
2. You may satisfy the conditions in Section 3(a)(1) in any
reasonable manner based on the medium, means, and context in
which You Share the Licensed Material. For example, it may be
reasonable to satisfy the conditions by providing a URI or
hyperlink to a resource that includes the required
information.
3. If requested by the Licensor, You must remove any of the
information required by Section 3(a)(1)(A) to the extent
reasonably practicable.
Section 4 -- Sui Generis Database Rights.
Where the Licensed Rights include Sui Generis Database Rights that
apply to Your use of the Licensed Material:
a. for the avoidance of doubt, Section 2(a)(1) grants You the right
to extract, reuse, reproduce, and Share all or a substantial
portion of the contents of the database for NonCommercial purposes
only and provided You do not Share Adapted Material;
b. if You include all or a substantial portion of the database
contents in a database in which You have Sui Generis Database
Rights, then the database in which You have Sui Generis Database
Rights (but not its individual contents) is Adapted Material; and
c. You must comply with the conditions in Section 3(a) if You Share
all or a substantial portion of the contents of the database.
For the avoidance of doubt, this Section 4 supplements and does not
replace Your obligations under this Public License where the Licensed
Rights include other Copyright and Similar Rights.
Section 5 -- Disclaimer of Warranties and Limitation of Liability.
a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
c. The disclaimer of warranties and limitation of liability provided
above shall be interpreted in a manner that, to the extent
possible, most closely approximates an absolute disclaimer and
waiver of all liability.
Section 6 -- Term and Termination.
a. This Public License applies for the term of the Copyright and
Similar Rights licensed here. However, if You fail to comply with
this Public License, then Your rights under this Public License
terminate automatically.
b. Where Your right to use the Licensed Material has terminated under
Section 6(a), it reinstates:
1. automatically as of the date the violation is cured, provided
it is cured within 30 days of Your discovery of the
violation; or
2. upon express reinstatement by the Licensor.
For the avoidance of doubt, this Section 6(b) does not affect any
right the Licensor may have to seek remedies for Your violations
of this Public License.
c. For the avoidance of doubt, the Licensor may also offer the
Licensed Material under separate terms or conditions or stop
distributing the Licensed Material at any time; however, doing so
will not terminate this Public License.
d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
License.
Section 7 -- Other Terms and Conditions.
a. The Licensor shall not be bound by any additional or different
terms or conditions communicated by You unless expressly agreed.
b. Any arrangements, understandings, or agreements regarding the
Licensed Material not stated herein are separate from and
independent of the terms and conditions of this Public License.
Section 8 -- Interpretation.
a. For the avoidance of doubt, this Public License does not, and
shall not be interpreted to, reduce, limit, restrict, or impose
conditions on any use of the Licensed Material that could lawfully
be made without permission under this Public License.
b. To the extent possible, if any provision of this Public License is
deemed unenforceable, it shall be automatically reformed to the
minimum extent necessary to make it enforceable. If the provision
cannot be reformed, it shall be severed from this Public License
without affecting the enforceability of the remaining terms and
conditions.
c. No term or condition of this Public License will be waived and no
failure to comply consented to unless expressly agreed to by the
Licensor.
d. Nothing in this Public License constitutes or may be interpreted
as a limitation upon, or waiver of, any privileges and immunities
that apply to the Licensor or You, including from the legal
processes of any jurisdiction or authority.
=======================================================================
Creative Commons is not a party to its public
licenses. Notwithstanding, Creative Commons may elect to apply one of
its public licenses to material it publishes and in those instances
will be considered the “Licensor.” The text of the Creative Commons
public licenses is dedicated to the public domain under the CC0 Public
Domain Dedication. Except for the limited purpose of indicating that
material is shared under a Creative Commons public license or as
otherwise permitted by the Creative Commons policies published at
creativecommons.org/policies, Creative Commons does not authorize the
use of the trademark "Creative Commons" or any other trademark or logo
of Creative Commons without its prior written consent including,
without limitation, in connection with any unauthorized modifications
to any of its public licenses or any other arrangements,
understandings, or agreements concerning use of licensed material. For
the avoidance of doubt, this paragraph does not form part of the
public licenses.
Creative Commons may be contacted at creativecommons.org.

70
README.md Normal file
View File

@@ -0,0 +1,70 @@
---
base_model:
- THUDM/glm-4-9b-chat
language:
- en
- zh
license: cc-by-nc-nd-4.0
tags:
- instruction-finetuning
inference: false
task_categories:
- text-generation
pipeline_tag: text-generation
library_name: transformers
---
<h1 align="center">
🔍 xVerify-9B-C
</h1>
<p align="center">
<div style="display: flex; justify-content: center; gap: 10px;">
<a href="https://github.com/IAAR-Shanghai/xVerify">
<img src="https://img.shields.io/badge/GitHub-Repository-blue?logo=github" alt="GitHub"/>
</a>
<a href="https://huggingface.co/IAAR-Shanghai/xVerify-9B-C">
<img src="https://img.shields.io/badge/🤗%20Hugging%20Face-xVerify--9B--C-yellow" alt="Hugging Face"/>
</a>
<a href="https://huggingface.co/papers/2504.10481">
<img src="https://img.shields.io/badge/Paper-Arxiv-red" alt="Paper"/>
</a>
</div>
</p>
xVerify is an evaluation tool fine-tuned from a pre-trained large language model, designed specifically for objective questions with a single correct answer. It was introduced in the paper [xVerify: Efficient Answer Verifier for Reasoning Model Evaluations](https://huggingface.co/papers/2504.10481).
It accurately extracts the final answer from lengthy reasoning processes and efficiently identifies equivalence across different forms of expressions.
---
## ✨ Key Features
### 📊 Broad Applicability
Suitable for various objective question evaluation scenarios including math problems, multiple-choice questions, classification tasks, and short-answer questions.
### ⛓️ Handles Long Reasoning Chains
Effectively processes answers with extensive reasoning steps to extract the final answer, regardless of complexity.
### 🌐 Multilingual Support
Primarily handles Chinese and English responses while remaining compatible with other languages.
### 🔄 Powerful Equivalence Judgment
- ✓ Recognizes basic transformations like letter case changes and Greek letter conversions
- ✓ Identifies equivalent mathematical expressions across formats (LaTeX, fractions, scientific notation)
- ✓ Determines semantic equivalence in natural language answers
- ✓ Matches multiple-choice responses by content rather than just option identifiers
---
## 📚 Citation
```bibtex
@article{xVerify,
title={xVerify: Efficient Answer Verifier for Reasoning Model Evaluations},
author={Ding Chen and Qingchen Yu and Pengyuan Wang and Wentao Zhang and Bo Tang and Feiyu Xiong and Xinchi Li and Minchuan Yang and Zhiyu Li},
journal={arXiv preprint arXiv:2504.10481},
year={2025},
}
```

16
added_tokens.json Normal file
View File

@@ -0,0 +1,16 @@
{
"<eop>": 151334,
"<sop>": 151333,
"<|assistant|>": 151337,
"<|begin_of_image|>": 151339,
"<|begin_of_video|>": 151341,
"<|end_of_image|>": 151340,
"<|end_of_video|>": 151342,
"<|endoftext|>": 151329,
"<|observation|>": 151338,
"<|system|>": 151335,
"<|user|>": 151336,
"[MASK]": 151330,
"[gMASK]": 151331,
"[sMASK]": 151332
}

50
config.json Normal file
View File

@@ -0,0 +1,50 @@
{
"_name_or_path": "/mnt/public/model/xverify/glm-4-9b-chat",
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"ChatGLMForConditionalGeneration"
],
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"auto_map": {
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
},
"bias_dropout_fusion": true,
"classifier_dropout": null,
"eos_token_id": [
151329,
151336,
151338
],
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1.5625e-07,
"model_type": "chatglm",
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_layers": 40,
"original_rope": true,
"pad_token_id": 151329,
"padded_vocab_size": 151552,
"post_layer_norm": true,
"rmsnorm": true,
"rope_ratio": 500,
"seq_length": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.46.3",
"use_cache": true,
"vocab_size": 151552
}

58
configuration_chatglm.py Normal file
View File

@@ -0,0 +1,58 @@
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,
classifier_dropout=None,
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,
rope_ratio=1,
apply_query_key_layer_scaling=True,
attention_softmax_in_fp32=True,
fp32_residual_connection=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.classifier_dropout = classifier_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.rope_ratio = rope_ratio
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
super().__init__(**kwargs)

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"do_sample": true,
"eos_token_id": [
151329,
151336,
151338
],
"max_length": 128000,
"pad_token_id": 151329,
"temperature": 0.8,
"top_p": 0.8,
"transformers_version": "4.46.3"
}

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d7108b6dd8eaca9dfc1a99b49b4c8daa27503fb669cde66b805065dbaaaaca5
size 4984147224

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9ab2a7887f1516177169bdf74e48b993500763d5f11f2cf7b1c8dff73435b6de
size 4895071360

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4522fc117dcb97b591748c4ab66a8679a93c319dca8a1f5d1e487fc6111be52c
size 4895071384

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e106a96f7d5564027c357dd3b9f08a5dae524c3da11db874531278989ea2849
size 4025651256

291
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,291 @@
{
"metadata": {
"total_size": 18799902784
},
"weight_map": {
"transformer.embedding.word_embeddings.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.final_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.10.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.11.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.12.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.13.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.14.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.15.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.16.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.17.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.18.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.19.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.20.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.21.self_attention.dense.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.22.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.23.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.24.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.25.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.26.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.27.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.28.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.29.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.30.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.31.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.32.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.33.self_attention.dense.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
"transformer.encoder.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.34.self_attention.dense.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.35.self_attention.dense.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.36.self_attention.dense.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.37.self_attention.dense.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.38.self_attention.dense.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.39.self_attention.dense.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
"transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.5.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.6.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.7.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.8.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
"transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.9.self_attention.dense.weight": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
"transformer.output_layer.weight": "model-00004-of-00004.safetensors",
"transformer.rotary_pos_emb.inv_freq": "model-00001-of-00004.safetensors"
}
}

1138
modeling_chatglm.py Normal file
View File

File diff suppressed because it is too large Load Diff

32
special_tokens_map.json Normal file
View File

@@ -0,0 +1,32 @@
{
"additional_special_tokens": [
"<|endoftext|>",
"[MASK]",
"[gMASK]",
"[sMASK]",
"<sop>",
"<eop>",
"<|system|>",
"<|user|>",
"<|assistant|>",
"<|observation|>",
"<|begin_of_image|>",
"<|end_of_image|>",
"<|begin_of_video|>",
"<|end_of_video|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

224
tokenization_chatglm.py Normal file
View File

@@ -0,0 +1,224 @@
import regex as re
import base64
import os
import tiktoken
from typing import List, Optional, Union, Dict
from transformers import PreTrainedTokenizer
from transformers.utils import PaddingStrategy
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
class ChatGLM4Tokenizer(PreTrainedTokenizer):
vocab_files_names = {"vocab_file": "tokenizer.model"}
model_input_names = ["input_ids", "attention_mask", "position_ids"]
def __init__(
self,
vocab_file,
clean_up_tokenization_spaces=False,
**kwargs
):
self.name = "GLM4Tokenizer"
self.vocab_file = vocab_file
pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
self.pat_str = re.compile(pat_str)
mergeable_ranks = {}
with open(vocab_file) as f:
for line in f:
token, rank = line.strip().split()
rank = int(rank)
token = base64.b64decode(token)
mergeable_ranks[token] = rank
self.mergeable_ranks = mergeable_ranks
self.tokenizer = tiktoken.Encoding(
name="my_tokenizer",
pat_str=pat_str,
mergeable_ranks=mergeable_ranks,
special_tokens={}
)
self.decoder = {rank: token for token, rank in mergeable_ranks.items()}
self.n_words = len(self.decoder)
super().__init__(
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
**kwargs
)
@property
def vocab_size(self):
return self.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 convert_tokens_to_string(self, tokens: List[Union[bytes, str, int]]) -> str:
"""
Converts a sequence of tokens in a single string.
"""
text = ""
temp = b""
for t in tokens:
if isinstance(t, int):
t = chr(t)
if isinstance(t, str):
if temp:
text += temp.decode("utf-8", errors="replace")
elif isinstance(t, bytes):
temp += t
else:
raise TypeError("token should only be of type int, bytes or str")
if temp:
text += temp.decode("utf-8", errors="replace")
return text
def _tokenize(self, text, **kwargs):
tokens = []
ids = self.tokenizer.encode(text)
for t in ids:
tokens.append(self.decoder[t])
return tokens
def _convert_token_to_id(self, token):
""" Converts a token (str) in an id using the vocab. """
return self.mergeable_ranks[token]
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
return self.decoder.get(index, "")
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.convert_tokens_to_ids("[gMASK]"), self.convert_tokens_to_ids("<sop>")]
return prefix_tokens
def build_single_message(self, role, metadata, message, tokenize=True):
assert role in ["system", "user", "assistant", "observation"], role
if tokenize:
role_tokens = [self.convert_tokens_to_ids(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n",
disallowed_special=())
message_tokens = self.tokenizer.encode(message, disallowed_special=())
tokens = role_tokens + message_tokens
return tokens
else:
return str(f"<|{role}|>{metadata}\n{message}")
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.convert_tokens_to_ids("<eos>")]
return token_ids_0
def _pad(
self,
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
max_length: Optional[int] = None,
padding_side: str = "left",
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
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 "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
return encoded_inputs

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
size 2623634

148
tokenizer_config.json Normal file
View File

@@ -0,0 +1,148 @@
{
"added_tokens_decoder": {
"151329": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151330": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151331": {
"content": "[gMASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151332": {
"content": "[sMASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151333": {
"content": "<sop>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151334": {
"content": "<eop>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151335": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151336": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151337": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151338": {
"content": "<|observation|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151339": {
"content": "<|begin_of_image|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151340": {
"content": "<|end_of_image|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151341": {
"content": "<|begin_of_video|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151342": {
"content": "<|end_of_video|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|endoftext|>",
"[MASK]",
"[gMASK]",
"[sMASK]",
"<sop>",
"<eop>",
"<|system|>",
"<|user|>",
"<|assistant|>",
"<|observation|>",
"<|begin_of_image|>",
"<|end_of_image|>",
"<|begin_of_video|>",
"<|end_of_video|>"
],
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLM4Tokenizer",
null
]
},
"chat_template": "{{ '[gMASK]<sop>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|assistant|>' }}{% elif message['role'] == 'assistant' %}{{ '\n' + content }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "<|endoftext|>",
"model_max_length": 128000,
"pad_token": "<|endoftext|>",
"padding_side": "left",
"remove_space": false,
"split_special_tokens": false,
"tokenizer_class": "ChatGLM4Tokenizer"
}