allenai/open-instruct-pythia-6.9b-tulu
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: allenai/open-instruct-pythia-6.9b-tulu
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-22 14:01:13 +08:00
commit 57a470fcc2
14 changed files with 101618 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
.gitattributes vendored Normal file
View File

@@ -0,0 +1,37 @@
*.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
*.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
pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text

179
LICENSE.txt Normal file
View File

@@ -0,0 +1,179 @@
AI MODEL LICENSE AGREEMENT
This License Agreement (as may be amended in accordance with this License Agreement, “License”), between you, or your employer or other entity (if you are entering into this agreement on behalf of your employer or other entity) (“Licensee” or “you”) and The Allen Institute for Artificial Intelligence a Washington nonprofit corporation recognized as tax exempt under Section 501(c)(3) of the Internal Revenue Code (“AI2” or “we”) applies to your use of any algorithm, and/or parameters that are made available by AI2 under this License (the “Model(s)”) and any specifications, manuals, documentation, and other written information provided by AI2 related to the Model (“Documentation”).
x
By clicking “I Accept” below or by using the Model, you agree to the terms of this License. If you do not agree to this License, then you do not have any rights to use the Model or Documentation (collectively, the “Model Components”), and you must immediately cease using the Model Components. If you are agreeing to be bound by the terms of this License on behalf of your employer or other entity, you represent and warrant to AI2 that you have full legal authority to bind your employer or such entity to this License. If you do not have the requisite authority, you may not accept the License or access the Model Components on behalf of your employer or other entity.
1. LICENSE GRANT
1. Subject to your compliance with the Documentation and Sections 2, 3, and 5, AI2 grants you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty free and limited license under AI2’s copyright interests to reproduce, distribute, and create derivative works of the Model solely for your non-commercial research purposes. The foregoing license is personal to you, and you may not assign or sublicense this License or any other rights or obligations under this License without AI2’s prior written consent; any such assignment or sublicense will be void and will automatically and immediately terminate this License.
2. You may make a reasonable number of copies of the Documentation solely for use in connection with the license to the Model granted above.
3. The grant of rights expressly set forth in this Section 1 (License Grant) are the complete grant of rights to you in the Model Components, and no other licenses are granted, whether by waiver, estoppel, implication, equity or otherwise. AI2 and its licensors reserve all rights not expressly granted by this License.
4. Except as set forth herein, AI2 claims no rights in the results you may produce or generate from the Model Components using informational content from any source (the “Output”). You are accountable for the Output you produce or generate from the Model Components and the subsequent use of that Output. No use of the Output can contravene any provision as stated in this License.
2. RESTRICTIONS
You will not, and will not permit, assist or cause any third party to:
5. Use, modify, copy, reproduce, create derivative works of, or distribute the Model Components (or any derivative works thereof, works incorporating the Model Components, or any data produced by the Model), in whole or in part, for (i) any commercial or production purposes, (ii) military purposes or in the service of nuclear technology, (iii) purposes of surveillance, including any research or development relating to surveillance, (iv) biometric processing, (v) in any manner that infringes, misappropriates, or otherwise violates any third-party rights, or (vi) in any manner that violates any applicable law and violating any privacy or security laws, rules, regulations, directives, or governmental requirements (including the General Data Privacy Regulation (Regulation (EU) 2016/679), the California Consumer Privacy Act, and any and all laws governing the processing of biometric information), as well as all amendments and successor laws to any of the foregoing;
6. Alter or remove copyright and other proprietary notices which appear on or in the Model Components;
7. Utilize any equipment, device, software, or other means to circumvent or remove any security or protection used by AI2 in connection with the Model, or to circumvent or remove any usage restrictions, or to enable functionality disabled by AI2;
8. Offer or impose any terms on the Model Components that alter, restrict, or are inconsistent with the terms of this License;
9. Use the Model in service of any of the Restricted Uses identified in Appendix A to this Agreement; or
10. Violate any applicable U.S. and non-U.S. export control and trade sanctions laws (“Export Laws”), including by, for example but without limitation:
1. directly or indirectly exporting, re-exporting, providing, or otherwise transferring Model Components:
1. to any individual, entity, or country prohibited by Export Laws;
2. to anyone on U.S. or non-U.S. government restricted parties lists; or
3. for any purpose prohibited by Export Laws, including nuclear, chemical or biological weapons, or missile technology applications;
2. using or downloading Model Components if you or they are
1. located in a comprehensively sanctioned jurisdiction;
2. currently listed on any U.S. or non-U.S. restricted parties list; or
3. for any purpose prohibited by Export Laws; and/or
3. disguising your location through IP proxying or other methods.
3. ATTRIBUTION
Together with any copies of the Model Components (as well as derivative works thereof or works incorporating the Model Components) that you distribute, you must provide
1. a copy of this License; and
2. the following attribution notice: open-instruct-pythia-6.9b-tulu is licensed under the AI Model License, Copyright © The Allen Institute for Artificial Intelligence. All Rights Reserved.”
4. DISCLAIMERS
THE MODEL COMPONENTS ARE PROVIDED “AS IS” and “WITH ALL FAULTS” WITH NO WARRANTY OF ANY KIND, EXPRESS OR IMPLIED. AI2 EXPRESSLY DISCLAIMS ALL REPRESENTATIONS AND WARRANTIES, EXPRESS OR IMPLIED, WHETHER BY STATUTE, CUSTOM, USAGE OR OTHERWISE AS TO ANY MATTERS RELATED TO THE MODEL COMPONENTS, INCLUDING BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, SATISFACTORY QUALITY, OR NON-INFRINGEMENT. AI2 MAKES NO WARRANTIES OR REPRESENTATIONS THAT THE MODEL COMPONENTS WILL BE ERROR FREE OR FREE OF VIRUSES OR OTHER HARMFUL COMPONENTS, OR PRODUCE ANY PARTICULAR RESULTS.
5. LIMITATION OF LIABILITY/YOUR RESPONSIBILITIES
3. TO THE FULLEST EXTENT PERMITTED BY LAW, IN NO EVENT WILL AI2 BE LIABLE TO YOU (i) UNDER ANY THEORY OF LIABILITY, WHETHER BASED IN CONTRACT, TORT, NEGLIGENCE, STRICT LIABILITY, WARRANTY, OR OTHERWISE UNDER THIS LICENSE, OR (ii) FOR ANY INDIRECT, CONSEQUENTIAL, EXEMPLARY, INCIDENTAL, PUNITIVE OR SPECIAL DAMAGES OR LOST PROFITS, EVEN IF YOU HAVE BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. THE MODEL COMPONENTS, THEIR CONSTITUENT COMPONENTS, AND ANY OUTPUT (COLLECTIVELY, “MODEL MATERIALS”) ARE NOT DESIGNED OR INTENDED FOR USE IN ANY APPLICATION OR SITUATION WHERE FAILURE OR FAULT OF THE MODEL MATERIALS COULD REASONABLY BE ANTICIPATED TO LEAD TO SERIOUS INJURY OF ANY PERSON, INCLUDING POTENTIAL DISCRIMINATION OR VIOLATION OF AN INDIVIDUAL’S PRIVACY RIGHTS, OR TO SEVERE PHYSICAL, PROPERTY, OR ENVIRONMENTAL DAMAGE (EACH, A “HIGH-RISK USE”).
4. IF YOU ELECT TO USE ANY OF THE MODEL MATERIALS FOR A HIGH-RISK USE, YOU DO SO AT YOUR OWN RISK. YOU AGREE TO DESIGN AND IMPLEMENT APPROPRIATE DECISION-MAKING AND RISK-MITIGATION PROCEDURES AND POLICIES IN CONNECTION WITH A HIGH-RISK USE SUCH THAT EVEN IF THERE IS A FAILURE OR FAULT IN ANY OF THE MODEL MATERIALS, THE SAFETY OF PERSONS OR PROPERTY AFFECTED BY THE ACTIVITY STAYS AT A LEVEL THAT IS REASONABLE, APPROPRIATE, AND LAWFUL FOR THE FIELD OF THE HIGH-RISK USE.
6. INDEMNIFICATION
You will indemnify, defend and hold harmless AI2 and our subsidiaries and affiliates, and each of our respective shareholders, directors, officers, employees, agents, successors, and assigns (collectively, the “AI2 Parties”) from and against any losses, liabilities, damages, fines, penalties, and expenses (including reasonable attorneys’ fees) incurred by any AI2 Party in connection with any claim, demand, allegation, lawsuit, proceeding, or investigation (collectively, “Claims”) arising out of or related to: (a) your access to or use of the Model Components (as well as any results or data generated from such access or use), including any High-Risk Use (defined below); (b) your violation of this License; or (c) your violation, misappropriation or infringement of any rights of another (including intellectual property or other proprietary rights and privacy rights). You will promptly notify the AI2 Parties of any such Claims, and cooperate with AI2 Parties in defending such Claims. You will also grant the AI2 Parties sole control of the defense or settlement, at AI2’s sole option, of any Claims. This indemnity is in addition to, and not in lieu of, any other indemnities or remedies set forth in a written agreement between you and AI2 or the other AI2 Parties.
7. TERMINATION; SURVIVAL
5. This License will automatically terminate upon any breach by you of the terms of this License.
b. We may terminate this License, in whole or in part, at any time upon notice (including electronic) to you.
c. The following sections survive termination of this License: 2 (Restrictions), 3 (Attribution), 4 (Disclaimers), 5 (Limitation on Liability), 6 (Indemnification) 7 (Termination; Survival), 8 (Third Party Materials), 9 (Trademarks), 10 (Applicable Law; Dispute Resolution), and 11 (Miscellaneous).
8. THIRD PARTY MATERIALS
The Model Components may contain third-party software or other components (including free and open source software) (all of the foregoing, “Third Party Materials”), which are subject to the license terms of the respective third-party licensors. Your dealings or correspondence with third parties and your use of or interaction with any Third Party Materials are solely between you and the third party. AI2 does not control or endorse, and makes no representations or warranties regarding, any Third Party Materials, and your access to and use of such Third Party Materials are at your own risk.
9. TRADEMARKS
Licensee has not been granted any trademark license as part of this License and may not use any name or mark associated with AI2 without the prior written permission of AI2, except to the extent necessary to make the reference required by the “ATTRIBUTION” section of this Agreement.
10. APPLICABLE LAW; DISPUTE RESOLUTION
This License will be governed and construed under the laws of the State of Washington without regard to conflicts of law provisions.
11. MISCELLANEOUS
If any provision or part of a provision of this License is unlawful, void or unenforceable, that provision or part of the provision is deemed severed from this License and will not affect the validity and enforceability of any remaining provisions. The failure of AI2 to exercise or enforce any right or provision of this License will not operate as a waiver of such right or provision. This License does not confer any third-party beneficiary rights upon any other person or entity. This License, together with the Documentation, contains the entire understanding between you and AI2 regarding the subject matter of this License, and supersedes all other written or oral agreements and understandings between you and AI2 regarding such subject matter. No change or addition to any provision of this License will be binding unless it is in writing and signed by an authorized representative of both you and AI2.
________________
Appendix A
1. USE-BASED RESTRICTIONS
You agree not to use the Model:
6. In any way that violates any applicable national, federal, state, local or international law or regulation;
7. For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
8. To generate or disseminate verifiably false information with the purpose of harming others;
9. To generate or disseminate personal identifiable information that can be used to harm an individual;
10. To generate or disseminate information or content, in any context (e.g. posts, articles, tweets, chatbots or other kinds of automated bots) without expressly and intelligibly disclaiming that the text is machine generated;
11. To defame, disparage or otherwise harass others;
12. To impersonate or attempt to impersonate others;
13. For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
14. For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics
15. To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
16. For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
17. To provide medical advice and medical results interpretation;
18. To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
2. DOMAIN-SPECIFIC RESTRICTIONS:
You agree not to use the Model to:
1. Surveillance:
4. Detect or infer any legally protected class or aspect of any person, as defined by U.S. Federal Law; or
5. Detect or infer aspects and/or features of an identity any person, such as name, family name, address, gender, sexual orientation, race, religion, age, location (at any geographical level), skin color, society or political affiliations, employment status and/or employment history, and health and medical conditions. Age and medical conditions may be inferred solely for the purpose of improving software/hardware accessibility and such data should not be cached or stored without the explicit and time limited permission of the data subject.
2. Computer Generated Media:
1. Synthesize and/or modify audio-realistic and/or video-realistic representations (indistinguishable from photo/video recordings) of people and events, without including a caption and/or watermark or other similar notation indicating that the audio-realistic and/or video-realistic representations were generated using the Model.
3. Insurance.
1. Predict the likelihood that any person will request to file an insurance claim;
2. Determine an insurance premium or deny insurance applications or claims;
3. Predict the likelihood that any person request to file an insurance claim based on determining a lifestyle of a person, medical-test reports, demographic details of a person and/or online activity of a person;
4. Determine an insurance premium or deny insurance applications or claims based on data determining a lifestyle of a person, medical-test reports, demographic details of a person, and/or online activity of a person;
5. Deny an insurance claim based on any predicted likelihood of the possibility of insurance fraud.
4. Medical.
1. diagnose or fail to diagnose a medical condition without human oversight.
5. Criminal.
2. use personal data or characteristics, physical attributes or traits, or other social or behavioral information to predict the likelihood a person will engage or has engaged in criminal behavior, including without limitation: name, family name, address, gender, sexual orientation, race, religion, age, location (at any geographical level), skin color, society or political affiliations, employment status and/or history, health and medical conditions (including physical, mental), family history, social media and publicly available data, image or video analysis of an individual or a group(s) of individuals, heart-rate, perspiration, breathing, and brain imaging and other metabolic data.

115
README.md Normal file
View File

@@ -0,0 +1,115 @@
---
datasets:
- databricks/databricks-dolly-15k
- OpenAssistant/oasst1
- sahil2801/CodeAlpaca-20k
language:
- en
---
# Pythia 6.9B Tulu
This model is a 6.9B Pythia model finetuned on a mixture of instruction datasets (FLAN V2, CoT, Dolly, Open Assistant 1, GPT4-Alpaca, Code-Alpaca, and ShareGPT).
This was trained as part of the paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://arxiv.org/abs/2306.04751).
The codebase used to train and evaluate this model can be found at [https://github.com/allenai/open-instruct](https://github.com/allenai/open-instruct).
This model is licensed under the AI model license given in LICENSE.txt, with the original model license at pythia_license.txt.
## Usage
Simply download and use - this model is not a diff, unlike the other open-instruct models.
## Input Format
The model is trained to use the following format (note the newlines):
```
<|user|>
Your message here!
<|assistant|>
```
For best results, format all inputs in this manner. **Make sure to include a newline after `<|assistant|>`, this can affect generation quality quite a bit.**
## Performance
Here is the performance of this model across benchmarks explored in our paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://arxiv.org/abs/2306.04751):
| MMLU 0-shot | MMLU 5-shot | GSM Direct | GSM CoT | BBH Direct | BBH CoT | TydiQA Gold-Passage | TydiQA Closed-book | Codex-Eval Pass@1 | Codex-Eval Pass@10 | AlpacaFarm vs Davinci-003 | Average |
|:-----------:|:-----------:|:----------:|:-------:|:----------:|:-------:|:-------------------:|:------------------:|:-----------------:|:------------------:|:-------------------------:|---------|
| 34.1 | 34.6 | 3.5 | 15.5 | 31.3 | 27.8 | 33.4 | 3.8 | 14.3 | 21.4 | 9.2 | 19.8 |
If you use this model, please cite our work, the Pythia paper, and the original datasets:
```
@misc{wang2023far,
title={How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources},
author={Yizhong Wang and Hamish Ivison and Pradeep Dasigi and Jack Hessel and Tushar Khot and Khyathi Raghavi Chandu and David Wadden and Kelsey MacMillan and Noah A. Smith and Iz Beltagy and Hannaneh Hajishirzi},
year={2023},
eprint={2306.04751},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{biderman2023pythia,
title={Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling},
author={Stella Biderman and Hailey Schoelkopf and Quentin Anthony and Herbie Bradley and Kyle O'Brien and Eric Hallahan and Mohammad Aflah Khan and Shivanshu Purohit and USVSN Sai Prashanth and Edward Raff and Aviya Skowron and Lintang Sutawika and Oskar van der Wal},
year={2023},
eprint={2304.01373},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{dolly,
author = {Databricks},
title = {Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {Blog post},
url = {https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm}
}
```
```
@article{longpre2023flan,
title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning},
author={Longpre, Shayne and Hou, Le and Vu, Tu and Webson, Albert and Chung, Hyung Won and Tay, Yi and Zhou, Denny and Le, Quoc V and Zoph, Barret and Wei, Jason and others},
journal={arXiv preprint arXiv:2301.13688},
year={2023}
}
```
```
@misc{köpf2023openassistant,
title={OpenAssistant Conversations -- Democratizing Large Language Model Alignment},
author={Andreas Köpf and Yannic Kilcher and Dimitri von Rütte and Sotiris Anagnostidis and Zhi-Rui Tam and Keith Stevens and Abdullah Barhoum and Nguyen Minh Duc and Oliver Stanley and Richárd Nagyfi and Shahul ES and Sameer Suri and David Glushkov and Arnav Dantuluri and Andrew Maguire and Christoph Schuhmann and Huu Nguyen and Alexander Mattick},
year={2023},
eprint={2304.07327},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@article{peng2023instruction,
title={Instruction Tuning with GPT-4},
author={Peng, Baolin and Li, Chunyuan and He, Pengcheng and Galley, Michel and Gao, Jianfeng},
journal={arXiv preprint arXiv:2304.03277},
year={2023}
}
```
```
@misc{codealpaca,
author = {Sahil Chaudhary},
title = {Code Alpaca: An Instruction-following LLaMA model for code generation},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/sahil280114/codealpaca}},
}
```

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "/model",
"architectures": [
"GPTNeoXForCausalLM"
],
"bos_token_id": 0,
"classifier_dropout": 0.1,
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 16384,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.30.1",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50278
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": 0,
"transformers_version": "4.30.1"
}

201
pythia_license.txt Normal file
View 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 2023 EleutherAI
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.

3
pytorch_model-00001-of-00003.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40106fa293b4d9dbabb9e264f5cf628d1c50445e1ca7d8643e7ba025f681b61e
size 10003427906

3
pytorch_model-00002-of-00003.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47895defbeb164af0f9f353abbfa2e14336e1506c812094ca6629e640532499c
size 9985128733

3
pytorch_model-00003-of-00003.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5ad579ca35253b0cfc2ae4823036dfc023e7ee6f9668d3e2bd69d292b3cd10a
size 7569992162

491
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,491 @@
{
"metadata": {
"total_size": 27440941184.0
},
"weight_map": {
"embed_out.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.20.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"gpt_neox.layers.24.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.30.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.attention.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
}
}

6
special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<pad>",
"unk_token": "<|endoftext|>"
}

100538
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

9
tokenizer_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPTNeoXTokenizer",
"unk_token": "<|endoftext|>"
}