初始化项目，由ModelHub XC社区提供模型
Model: swiss-ai/Apertus-8B-2509 Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
203
LICENSE.txt
Normal file
203
LICENSE.txt
Normal file
@@ -0,0 +1,203 @@
|
||||
Copyright 2025 - The Swiss AI team.
|
||||
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright [yyyy] [name of copyright owner]
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
186
README.md
Normal file
186
README.md
Normal file
@@ -0,0 +1,186 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- multilingual
|
||||
- compliant
|
||||
- swiss-ai
|
||||
- apertus
|
||||
|
||||
extra_gated_prompt: "### Apertus LLM Acceptable Use Policy \n(1.0 | September 1, 2025)\n\"Agreement\" The Swiss National AI Institute (SNAI) is a partnership between the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL. \n\nBy using the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and EPFL against any third-party claims arising from your use of Apertus LLM. \n\nThe training data and the Apertus LLM may contain or generate information that directly or indirectly refers to an identifiable individual (Personal Data). You process Personal Data as independent controller in accordance with applicable data protection law. SNAI will regularly provide a file with hash values for download which you can apply as an output filter to your use of our Apertus LLM. The file reflects data protection deletion requests which have been addressed to SNAI as the developer of the Apertus LLM. It allows you to remove Personal Data contained in the model output. We strongly advise downloading and applying this output filter from SNAI every six months following the release of the model. "
|
||||
extra_gated_fields:
|
||||
Your Name: text
|
||||
Country: country
|
||||
Affiliation: text
|
||||
geo: ip_location
|
||||
By clicking Submit below I accept the terms of use: checkbox
|
||||
extra_gated_button_content: Submit
|
||||
---
|
||||
|
||||
# Apertus
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Model Summary](#model-summary)
|
||||
2. [How to use](#how-to-use)
|
||||
3. [Evaluation](#evaluation)
|
||||
4. [Training](#training)
|
||||
5. [Limitations](#limitations)
|
||||
6. [Legal Aspects](#legal-aspects)
|
||||
|
||||
## Model Summary
|
||||
|
||||
Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.
|
||||
The model supports over 1000 languages and long context, it uses only fully compliant and open training data, and achieves comparable performance to models trained behind closed doors.
|
||||
|
||||
|
||||
|
||||
The model is a decoder-only transformer, pretrained on 15T tokens with a staged curriculum of web, code and math data. The model uses a new xIELU activation function and is trained from scratch with the AdEMAMix optimizer. Post-training included supervised fine-tuning and alignment via QRPO.
|
||||
|
||||
### Key features
|
||||
- **Fully open model**: open weights + open data + full training details including all data and training recipes
|
||||
- **Massively Multilingual**: 1811 natively supported languages
|
||||
- **Compliant** Apertus is trained while respecting opt-out consent of data owners (even retrospectivey), and avoiding memorization of training data
|
||||
|
||||
For more details refer to our [technical report](https://arxiv.org/abs/2509.14233)
|
||||
|
||||
## How to use
|
||||
|
||||
The modeling code for Apertus is available in transformers `v4.56.0` and later, so make sure to upgrade your transformers version. You can also load the model with the latest `vLLM` which uses transformers as a backend.
|
||||
```bash
|
||||
pip install -U transformers
|
||||
```
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "swiss-ai/Apertus-8B-2509"
|
||||
device = "cuda" # for GPU usage or "cpu" for CPU usage
|
||||
|
||||
# load the tokenizer and the model
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
).to(device)
|
||||
|
||||
# prepare the model input
|
||||
prompt = "Give me a brief explanation of gravity in simple terms."
|
||||
messages_think = [
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages_think,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
|
||||
# Generate the output
|
||||
generated_ids = model.generate(**model_inputs, max_new_tokens=32768)
|
||||
|
||||
# Get and decode the output
|
||||
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]
|
||||
print(tokenizer.decode(output_ids, skip_special_tokens=True))
|
||||
```
|
||||
|
||||
>[!TIP]
|
||||
> We recommend setting `temperature=0.8` and `top_p=0.9` in the sampling parameters.
|
||||
|
||||
### Long context processing
|
||||
|
||||
Apertus by default supports a context length up to 65,536 tokens.
|
||||
|
||||
### Agentic Usage
|
||||
|
||||
Apertus supports tool use
|
||||
|
||||
### Deployment
|
||||
|
||||
Deployment of the models is directly supported by the newest versions of [Transformers](https://github.com/huggingface/transformers), [vLLM](https://github.com/vllm-project/vllm), [SGLang](https://github.com/sgl-project/sglang), and also for running on-device with [MLX](https://github.com/ml-explore/mlx-lm),
|
||||
|
||||
## Evaluation
|
||||
|
||||
**Pretraining Evaluation:** Performance (%) of Apertus models on *general language understanding* tasks (higher is better) compared to other pretrained models.
|
||||
|
||||
| **Model** | **Avg** | **ARC** | **HellaSwag** | **WinoGrande** | **XNLI** | **XCOPA** | **PIQA** |
|
||||
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
||||
| **Fully Open Models** | | | | | | | |
|
||||
| **Apertus-8B** | 65.8 | 72.7 | 59.8 | 70.6 | 45.2 | 66.5 | 79.8 |
|
||||
| **Apertus-70B** | 67.5 | 70.6 | 64.0 | 73.3 | 45.3 | 69.8 | 81.9 |
|
||||
| OLMo2-7B | 64.0 | 72.9 | 60.4 | 74.5 | 40.4 | 55.2 | 80.9 |
|
||||
| OLMo2-32B | 67.7 | 76.2 | 66.7 | 78.6 | 42.9 | 60.1 | 82.1 |
|
||||
| EuroLLM-1.7B | 54.8 | 57.2 | 44.9 | 58.1 | 40.7 | 55.7 | 72.4 |
|
||||
| EuroLLM-9B | 62.8 | 67.9 | 57.9 | 68.8 | 41.5 | 61.1 | 79.6 |
|
||||
| SmolLM2-1.7B | 58.5 | 66.1 | 52.4 | 65.6 | 37.6 | 52.3 | 77.0 |
|
||||
| SmolLM3-3B | 61.6 | 68.6 | 56.4 | 68.1 | 40.5 | 58.2 | 77.7 |
|
||||
| Poro-34B | 61.7 | 65.7 | 57.9 | 70.6 | 41.6 | 56.0 | 78.5 |
|
||||
| **Open-Weight Models** | | | | | | | |
|
||||
| Llama3.1-8B | 65.4 | 71.6 | 60.0 | 73.4 | 45.3 | 61.8 | 80.1 |
|
||||
| Llama3.1-70B | 67.3 | 74.4 | 56.5 | 79.4 | 44.3 | 66.7 | 82.3 |
|
||||
| Qwen2.5-7B | 64.4 | 69.6 | 60.1 | 72.8 | 43.3 | 61.7 | 78.7 |
|
||||
| Qwen2.5-72B | 69.8 | 76.2 | 67.5 | 78.0 | 46.9 | 68.2 | 82.0 |
|
||||
| Qwen3-32B | 67.8 | 75.6 | 64.0 | 73.8 | 44.4 | 67.9 | 80.9 |
|
||||
| Llama4-Scout-16x17B | 67.9 | 74.7 | 66.8 | 73.2 | 43.5 | 67.7 | 81.2 |
|
||||
| GPT-OSS-20B | 58.1 | 67.0 | 41.5 | 66.5 | 37.4 | 60.4 | 75.6 |
|
||||
|
||||
Many additional benchmark evaluations, for pretraining and posttraining phases, multilingual evaluations in around hundred languages, and long context evaluations are provided in Section 5 of the [Apertus_Tech_Report.pdf](https://github.com/swiss-ai/apertus-tech-report/blob/main/Apertus_Tech_Report.pdf)
|
||||
|
||||
## Training
|
||||
|
||||
### Model
|
||||
|
||||
- **Architecture:** Transformer decoder
|
||||
- **Pretraining tokens:** 15T
|
||||
- **Precision:** bfloat16
|
||||
|
||||
### Software & hardware
|
||||
|
||||
- **GPUs:** 4096 GH200
|
||||
- **Training Framework:** [Megatron-LM](https://github.com/swiss-ai/Megatron-LM)
|
||||
- ...
|
||||
|
||||
### Open resources
|
||||
All elements used in the training process are made openly available
|
||||
- **Training data reconstruction scripts:** [github.com/swiss-ai/pretrain-data](https://github.com/swiss-ai/pretrain-data)
|
||||
- The training intermediate checkpoints are available on the different branches of this same repository
|
||||
|
||||
|
||||
## Limitations
|
||||
|
||||
Apertus can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.
|
||||
|
||||
|
||||
## Legal Aspects
|
||||
|
||||
#### EU AI Act Transparency Documentation and Code of Practice
|
||||
- [Apertus_EU_Public_Summary.pdf](https://huggingface.co/swiss-ai/Apertus-70B-2509/blob/main/Apertus_EU_Public_Summary.pdf)
|
||||
- [Apertus_EU_Code_of_Practice.pdf](https://huggingface.co/swiss-ai/Apertus-70B-2509/blob/main/Apertus_EU_Code_of_Practice.pdf)
|
||||
|
||||
#### Data Protection and Copyright Requests
|
||||
For removal requests of personally identifiable information (PII) or of copyrighted content, please contact the respective dataset owners or us directly
|
||||
- llm-privacy-requests@swiss-ai.org
|
||||
- llm-copyright-requests@swiss-ai.org
|
||||
|
||||
#### Output Filter for PII
|
||||
- Currently no output filter is provided.
|
||||
- Please check this site regularly for an output filter that can be used on top of the Apertus LLM. The filter reflects data protection deletion requests which have been addressed to us as the developer of the Apertus LLM. It allows you to remove Personal Data contained in the model output. We strongly advise downloading and applying this output filter from this site every six months.
|
||||
|
||||
## Contact
|
||||
To contact us, please send an email to
|
||||
llm-requests@swiss-ai.org
|
||||
|
||||
## Citation
|
||||
```bash
|
||||
@misc{swissai2025apertus,
|
||||
title={{Apertus: Democratizing Open and Compliant LLMs for Global Language Environments}},
|
||||
author={Alejandro Hernández-Cano and Alexander Hägele and Allen Hao Huang and Angelika Romanou and Antoni-Joan Solergibert and Barna Pasztor and Bettina Messmer and Dhia Garbaya and Eduard Frank Ďurech and Ido Hakimi and Juan García Giraldo and Mete Ismayilzada and Negar Foroutan and Skander Moalla and Tiancheng Chen and Vinko Sabolčec and Yixuan Xu and Michael Aerni and Badr AlKhamissi and Ines Altemir Marinas and Mohammad Hossein Amani and Matin Ansaripour and Ilia Badanin and Harold Benoit and Emanuela Boros and Nicholas Browning and Fabian Bösch and Maximilian Böther and Niklas Canova and Camille Challier and Clement Charmillot and Jonathan Coles and Jan Deriu and Arnout Devos and Lukas Drescher and Daniil Dzenhaliou and Maud Ehrmann and Dongyang Fan and Simin Fan and Silin Gao and Miguel Gila and María Grandury and Diba Hashemi and Alexander Hoyle and Jiaming Jiang and Mark Klein and Andrei Kucharavy and Anastasiia Kucherenko and Frederike Lübeck and Roman Machacek and Theofilos Manitaras and Andreas Marfurt and Kyle Matoba and Simon Matrenok and Henrique Mendoncça and Fawzi Roberto Mohamed and Syrielle Montariol and Luca Mouchel and Sven Najem-Meyer and Jingwei Ni and Gennaro Oliva and Matteo Pagliardini and Elia Palme and Andrei Panferov and Léo Paoletti and Marco Passerini and Ivan Pavlov and Auguste Poiroux and Kaustubh Ponkshe and Nathan Ranchin and Javi Rando and Mathieu Sauser and Jakhongir Saydaliev and Muhammad Ali Sayfiddinov and Marian Schneider and Stefano Schuppli and Marco Scialanga and Andrei Semenov and Kumar Shridhar and Raghav Singhal and Anna Sotnikova and Alexander Sternfeld and Ayush Kumar Tarun and Paul Teiletche and Jannis Vamvas and Xiaozhe Yao and Hao Zhao Alexander Ilic and Ana Klimovic and Andreas Krause and Caglar Gulcehre and David Rosenthal and Elliott Ash and Florian Tramèr and Joost VandeVondele and Livio Veraldi and Martin Rajman and Thomas Schulthess and Torsten Hoefler and Antoine Bosselut and Martin Jaggi and Imanol Schlag},
|
||||
year={2025},
|
||||
howpublished={\url{https://arxiv.org/abs/2509.14233}}
|
||||
}
|
||||
```
|
||||
9
USAGE_POLICY.md
Normal file
9
USAGE_POLICY.md
Normal file
@@ -0,0 +1,9 @@
|
||||
Apertus LLM Acceptable Use Policy
|
||||
|
||||
(v1.0 | September 1, 2025)
|
||||
|
||||
The Swiss National AI Institute (SNAI) is a partnership between the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL.
|
||||
|
||||
By using the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and EPFL against any third-party claims arising from your use of Apertus LLM.
|
||||
|
||||
The training data and the Apertus LLM may contain or generate information that directly or indirectly refers to an identifiable individual (Personal Data). You process Personal Data as independent controller in accordance with applicable data protection law. SNAI will regularly provide a file with hash values for download which you can apply as an output filter to your use of our Apertus LLM. The file reflects data protection deletion requests which have been addressed to SNAI as the developer of the Apertus LLM. It allows you to remove Personal Data contained in the model output. We strongly advise downloading and applying this output filter from SNAI every six months following the release of the model.
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"architectures": [
|
||||
"ApertusForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "xielu",
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 21504,
|
||||
"max_position_embeddings": 65536,
|
||||
"mlp_bias": false,
|
||||
"model_type": "apertus",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 3,
|
||||
"post_norm": false,
|
||||
"qk_norm": true,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3",
|
||||
"type": "llama3"
|
||||
},
|
||||
"rope_theta": 12000000,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.54.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a7c21e1d777d7f5651191f50f3a873345c770fb49e384341d7e8584cd18f1402
|
||||
size 4999776656
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:79c2bd751b9c072de6cfeb97cc136d912b9d5cb2dcbbd9e30ed7b9cacb7f2b17
|
||||
size 4882374192
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:681c4e64ea0ea9171df8a9e1c283d88253d2a70b7d278ef2d99ab1cd6bcdaf18
|
||||
size 4974647808
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a1187bf39f8a7b2045be7e3c142b4a7bd2967668fcfad802800d82d976b9b6d
|
||||
size 1249928160
|
||||
459
model.safetensors.index.json
Normal file
459
model.safetensors.index.json
Normal file
@@ -0,0 +1,459 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8053338176,
|
||||
"total_size": 16106676480
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.alpha_n": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.alpha_p": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.beta": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.eps": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bb201fb226cde11f66c3cf51c5344fb37b1611f00c21e75c324546d854eff2e1
|
||||
size 17078480
|
||||
8020
tokenizer_config.json
Normal file
8020
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user