Text Generation
Transformers
Safetensors
livemem
qwen3
custom-code
long-context
reinforcement-learning
conversational
custom_code
Instructions to use chen-l/LiveMem-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chen-l/LiveMem-RL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="chen-l/LiveMem-RL", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("chen-l/LiveMem-RL", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use chen-l/LiveMem-RL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "chen-l/LiveMem-RL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chen-l/LiveMem-RL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/chen-l/LiveMem-RL
- SGLang
How to use chen-l/LiveMem-RL with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "chen-l/LiveMem-RL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chen-l/LiveMem-RL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "chen-l/LiveMem-RL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chen-l/LiveMem-RL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use chen-l/LiveMem-RL with Docker Model Runner:
docker model run hf.co/chen-l/LiveMem-RL
Add files using upload-large-folder tool
Browse files- .gitattributes +1 -34
- LICENSE +202 -0
- README.md +64 -0
- __init__.py +4 -0
- chat_template.jinja +61 -0
- config.json +86 -0
- configuration_livemem.py +61 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- modeling_livemem.py +496 -0
- modeling_livemem_gdn2.py +171 -0
- requirements.txt +4 -0
- tokenizer.json +3 -0
- tokenizer_config.json +29 -0
.gitattributes
CHANGED
|
@@ -1,35 +1,2 @@
|
|
| 1 |
-
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
-
|
| 27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
|
| 190 |
+
Copyright 2024 Alibaba Cloud
|
| 191 |
+
|
| 192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 193 |
+
you may not use this file except in compliance with the License.
|
| 194 |
+
You may obtain a copy of the License at
|
| 195 |
+
|
| 196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 197 |
+
|
| 198 |
+
Unless required by applicable law or agreed to in writing, software
|
| 199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 201 |
+
See the License for the specific language governing permissions and
|
| 202 |
+
limitations under the License.
|
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
base_model: chen-l/LiveMem-SFT
|
| 6 |
+
tags:
|
| 7 |
+
- livemem
|
| 8 |
+
- qwen3
|
| 9 |
+
- custom-code
|
| 10 |
+
- long-context
|
| 11 |
+
- reinforcement-learning
|
| 12 |
+
- text-generation
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# LiveMem-RL
|
| 16 |
+
|
| 17 |
+
LiveMem-RL is the reinforcement-learning checkpoint of LiveMem-4B-SFT. It
|
| 18 |
+
uses a Qwen3 attention path in parallel with a Gated DeltaNet 2 (GDN2)
|
| 19 |
+
recurrent memory path at every decoder layer:
|
| 20 |
+
|
| 21 |
+
```text
|
| 22 |
+
layer output = Qwen3 attention output + GDN2 memory output
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
This checkpoint was trained with GRPO from `chen-l/LiveMem-SFT`. During RL,
|
| 26 |
+
the Qwen3 main path remained frozen and the memory side path was updated. The
|
| 27 |
+
configured maximum context length is 262,144 tokens; actual usable context
|
| 28 |
+
depends on GPU memory and inference backend.
|
| 29 |
+
|
| 30 |
+
## Transformers usage
|
| 31 |
+
|
| 32 |
+
LiveMem uses custom model code and GDN2 Triton kernels. A CUDA environment is
|
| 33 |
+
required for inference.
|
| 34 |
+
|
| 35 |
+
```bash
|
| 36 |
+
pip install -r requirements.txt
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
```python
|
| 40 |
+
import torch
|
| 41 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 42 |
+
|
| 43 |
+
model_id = "chen-l/LiveMem-4B-RL"
|
| 44 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
| 45 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 46 |
+
model_id,
|
| 47 |
+
trust_remote_code=True,
|
| 48 |
+
dtype=torch.bfloat16,
|
| 49 |
+
device_map="auto",
|
| 50 |
+
)
|
| 51 |
+
|
| 52 |
+
messages = [{"role": "user", "content": "Answer using the supplied long context."}]
|
| 53 |
+
inputs = tokenizer.apply_chat_template(
|
| 54 |
+
messages,
|
| 55 |
+
add_generation_prompt=True,
|
| 56 |
+
return_tensors="pt",
|
| 57 |
+
return_dict=True,
|
| 58 |
+
).to(model.device)
|
| 59 |
+
outputs = model.generate(**inputs, max_new_tokens=256)
|
| 60 |
+
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
+
`trust_remote_code=True` is required because LiveMem is not a built-in
|
| 64 |
+
Transformers architecture.
|
__init__.py
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from .configuration_livemem import LiveMemConfig
|
| 2 |
+
from .modeling_livemem import LiveMemForCausalLM, LiveMemModel
|
| 3 |
+
|
| 4 |
+
__all__ = ["LiveMemConfig", "LiveMemModel", "LiveMemForCausalLM"]
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LiveMemForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_livemem.LiveMemConfig",
|
| 7 |
+
"AutoModel": "modeling_livemem.LiveMemModel",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_livemem.LiveMemForCausalLM"
|
| 9 |
+
},
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 151643,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 151645,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 2560,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 9728,
|
| 20 |
+
"layer_types": [
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"max_position_embeddings": 262144,
|
| 59 |
+
"max_window_layers": 36,
|
| 60 |
+
"mem_conv_bias": false,
|
| 61 |
+
"mem_conv_size": 4,
|
| 62 |
+
"mem_expand_v": 1.0,
|
| 63 |
+
"mem_head_dim": 128,
|
| 64 |
+
"mem_layers": null,
|
| 65 |
+
"mem_norm_eps": 1e-06,
|
| 66 |
+
"mem_num_heads": 32,
|
| 67 |
+
"mem_num_v_heads": 32,
|
| 68 |
+
"mem_o_proj_zero_init": true,
|
| 69 |
+
"memory_design": "X",
|
| 70 |
+
"model_type": "livemem",
|
| 71 |
+
"num_attention_heads": 32,
|
| 72 |
+
"num_hidden_layers": 36,
|
| 73 |
+
"num_key_value_heads": 8,
|
| 74 |
+
"pad_token_id": 151643,
|
| 75 |
+
"rms_norm_eps": 1e-06,
|
| 76 |
+
"rope_parameters": {
|
| 77 |
+
"rope_theta": 5000000,
|
| 78 |
+
"rope_type": "default"
|
| 79 |
+
},
|
| 80 |
+
"sliding_window": null,
|
| 81 |
+
"tie_word_embeddings": true,
|
| 82 |
+
"transformers_version": "5.12.1",
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_sliding_window": false,
|
| 85 |
+
"vocab_size": 151936
|
| 86 |
+
}
|
configuration_livemem.py
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Config for the memory-augmented Qwen3 (主路 Qwen3Attention ‖ 边路 GDN2)."""
|
| 2 |
+
from __future__ import annotations
|
| 3 |
+
|
| 4 |
+
from transformers.models.qwen3.configuration_qwen3 import Qwen3Config
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
class LiveMemConfig(Qwen3Config):
|
| 8 |
+
"""Qwen3 + per-attention-head GDN2 memory side-branch.
|
| 9 |
+
|
| 10 |
+
All base Qwen3 fields are inherited unchanged. The `mem_*` fields configure
|
| 11 |
+
the side branch and the two memory mechanisms (Design X / Design Y).
|
| 12 |
+
"""
|
| 13 |
+
|
| 14 |
+
model_type = "livemem"
|
| 15 |
+
|
| 16 |
+
def __init__(
|
| 17 |
+
self,
|
| 18 |
+
# which mechanism: "X" = 连续扫描 (continuous scan, write_mask=None);
|
| 19 |
+
# "Y" = 门控读写解耦 (freeze gates on read tokens).
|
| 20 |
+
memory_design: str = "Y",
|
| 21 |
+
# layers that get a memory branch; None = all layers.
|
| 22 |
+
mem_layers: list[int] | None = None,
|
| 23 |
+
# GDN2 side-branch hyper-params. The legacy/default geometry is a
|
| 24 |
+
# full-MHA copy of Qwen3 (8 KV heads repeated 4x -> 32 heads), per plan
|
| 25 |
+
# 02 §1.3. Newer experiments can explicitly set mem_num_heads=8,
|
| 26 |
+
# mem_num_v_heads=8, mem_expand_v=4 to keep similar state capacity with
|
| 27 |
+
# fewer Q/K heads.
|
| 28 |
+
mem_head_dim: int | None = None,
|
| 29 |
+
mem_num_heads: int | None = None,
|
| 30 |
+
mem_num_v_heads: int | None = None,
|
| 31 |
+
mem_expand_v: float = 1.0,
|
| 32 |
+
mem_conv_size: int = 4,
|
| 33 |
+
mem_conv_bias: bool = False,
|
| 34 |
+
mem_norm_eps: float | None = None,
|
| 35 |
+
# zero-init the side o_proj so training starts ≈ original Qwen3 (plan T1).
|
| 36 |
+
mem_o_proj_zero_init: bool = True,
|
| 37 |
+
**kwargs,
|
| 38 |
+
) -> None:
|
| 39 |
+
super().__init__(**kwargs)
|
| 40 |
+
if memory_design not in ("X", "Y"):
|
| 41 |
+
raise ValueError(f"memory_design must be 'X' or 'Y', got {memory_design!r}")
|
| 42 |
+
self.memory_design = memory_design
|
| 43 |
+
self.mem_layers = mem_layers
|
| 44 |
+
self.mem_head_dim = mem_head_dim if mem_head_dim is not None else self.head_dim
|
| 45 |
+
self.mem_num_heads = (
|
| 46 |
+
mem_num_heads if mem_num_heads is not None else self.num_attention_heads
|
| 47 |
+
)
|
| 48 |
+
self.mem_num_v_heads = (
|
| 49 |
+
mem_num_v_heads if mem_num_v_heads is not None else self.mem_num_heads
|
| 50 |
+
)
|
| 51 |
+
self.mem_expand_v = mem_expand_v
|
| 52 |
+
self.mem_conv_size = mem_conv_size
|
| 53 |
+
self.mem_conv_bias = mem_conv_bias
|
| 54 |
+
self.mem_norm_eps = mem_norm_eps if mem_norm_eps is not None else self.rms_norm_eps
|
| 55 |
+
self.mem_o_proj_zero_init = mem_o_proj_zero_init
|
| 56 |
+
|
| 57 |
+
@property
|
| 58 |
+
def memory_layer_indices(self) -> list[int]:
|
| 59 |
+
if self.mem_layers is None:
|
| 60 |
+
return list(range(self.num_hidden_layers))
|
| 61 |
+
return list(self.mem_layers)
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"transformers_version": "5.12.1",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a431577034b0ce43535d20fde78df765a19b992ad0130cdd7826e63fe5f13f0
|
| 3 |
+
size 12701729032
|
modeling_livemem.py
ADDED
|
@@ -0,0 +1,496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Memory-augmented Qwen3: 主路 Qwen3Attention ‖ 边路 GDN2, o = o_main + o_side.
|
| 2 |
+
|
| 3 |
+
Design X (continuous scan) and Design Y (gated read/write) share one skeleton
|
| 4 |
+
and the same attention eviction mask; they differ only in the RNN `write_mask`:
|
| 5 |
+
- X: write_mask = None (RNN scans every token; state = compression of all)
|
| 6 |
+
- Y: write_mask = is_evicted (open gate only on the evict/compress region)
|
| 7 |
+
"""
|
| 8 |
+
from __future__ import annotations
|
| 9 |
+
|
| 10 |
+
import torch
|
| 11 |
+
import torch.nn as nn
|
| 12 |
+
|
| 13 |
+
from transformers.cache_utils import Cache, DynamicCache
|
| 14 |
+
from transformers.masking_utils import create_causal_mask, create_sliding_window_causal_mask
|
| 15 |
+
from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
|
| 16 |
+
from transformers.models.qwen3.modeling_qwen3 import (
|
| 17 |
+
Qwen3Attention,
|
| 18 |
+
Qwen3ForCausalLM,
|
| 19 |
+
Qwen3Model,
|
| 20 |
+
Qwen3PreTrainedModel,
|
| 21 |
+
)
|
| 22 |
+
|
| 23 |
+
from .configuration_livemem import LiveMemConfig
|
| 24 |
+
from .modeling_livemem_gdn2 import LiveMemGatedDeltaNet2
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
def make_memory_and_mask(
|
| 28 |
+
is_evicted: torch.Tensor | None = None,
|
| 29 |
+
segment_ids: torch.Tensor | None = None,
|
| 30 |
+
seq_ids: torch.Tensor | None = None,
|
| 31 |
+
chunk_id: torch.Tensor | None = None,
|
| 32 |
+
evict_step: torch.Tensor | None = None,
|
| 33 |
+
):
|
| 34 |
+
"""Build an `and_mask_function` for `create_causal_mask` from up to four
|
| 35 |
+
constraints, AND-combined with causal by `create_causal_mask`:
|
| 36 |
+
|
| 37 |
+
- dynamic eviction (`chunk_id [B,T]`, `evict_step [B,T]` int): the real
|
| 38 |
+
training path. Each token belongs to a chunk; `evict_step[t]` is the chunk
|
| 39 |
+
step at which that token's chunk is evicted to the RNN state. keep(q,kv) =
|
| 40 |
+
`evict_step[kv] > chunk_id[q]` — key kv's chunk must still be live when
|
| 41 |
+
query q's chunk is processed (Design X: RNN scans all, attention evicts).
|
| 42 |
+
- static eviction (`is_evicted [B,T]` bool): the simple synthetic variant.
|
| 43 |
+
keep(q,kv) = (kv live) OR (q evicted).
|
| 44 |
+
- segments (`segment_ids [B,T]` int): keep(q,kv) = (kv shared, id==0) OR
|
| 45 |
+
(same segment). PACK block-diagonal QA.
|
| 46 |
+
- documents (`seq_ids [B,T]` int): keep(q,kv) = same document. cu_seqlens
|
| 47 |
+
packing isolation.
|
| 48 |
+
|
| 49 |
+
Returns None if no constraint is given. Works for flex_attention (BlockMask)
|
| 50 |
+
and sdpa/eager (vmapped) backends.
|
| 51 |
+
"""
|
| 52 |
+
preds = []
|
| 53 |
+
if chunk_id is not None and evict_step is not None:
|
| 54 |
+
preds.append(lambda b, q, kv: evict_step[b, kv] > chunk_id[b, q])
|
| 55 |
+
if is_evicted is not None:
|
| 56 |
+
preds.append(lambda b, q, kv: (~is_evicted[b, kv]) | is_evicted[b, q])
|
| 57 |
+
if segment_ids is not None:
|
| 58 |
+
preds.append(lambda b, q, kv: (segment_ids[b, kv] == 0) | (segment_ids[b, kv] == segment_ids[b, q]))
|
| 59 |
+
if seq_ids is not None:
|
| 60 |
+
preds.append(lambda b, q, kv: seq_ids[b, kv] == seq_ids[b, q])
|
| 61 |
+
if not preds:
|
| 62 |
+
return None
|
| 63 |
+
|
| 64 |
+
def and_mask(b, h, q, kv):
|
| 65 |
+
out = preds[0](b, q, kv)
|
| 66 |
+
for p in preds[1:]:
|
| 67 |
+
out = out & p(b, q, kv)
|
| 68 |
+
return out
|
| 69 |
+
|
| 70 |
+
return and_mask
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
# Backwards-compatible alias.
|
| 74 |
+
def make_evict_and_mask(is_evicted: torch.Tensor):
|
| 75 |
+
return make_memory_and_mask(is_evicted)
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
class LiveMemAttention(nn.Module):
|
| 79 |
+
"""Wraps the original Qwen3Attention (main path) and adds a GDN2 side branch.
|
| 80 |
+
|
| 81 |
+
Per-forward memory control (`write_mask`, side-branch cache) is set as
|
| 82 |
+
attributes by the model loop rather than threaded through kwargs, so the
|
| 83 |
+
base attention path and HF decorators never see custom kwargs.
|
| 84 |
+
"""
|
| 85 |
+
|
| 86 |
+
def __init__(self, base_attn: Qwen3Attention, config: LiveMemConfig) -> None:
|
| 87 |
+
super().__init__()
|
| 88 |
+
self.layer_idx = base_attn.layer_idx
|
| 89 |
+
self.attn = base_attn # main path: untouched Qwen3Attention
|
| 90 |
+
self.mem = LiveMemGatedDeltaNet2(
|
| 91 |
+
hidden_size=config.hidden_size,
|
| 92 |
+
expand_v=config.mem_expand_v,
|
| 93 |
+
head_dim=config.mem_head_dim,
|
| 94 |
+
num_heads=config.mem_num_heads,
|
| 95 |
+
num_v_heads=config.mem_num_v_heads,
|
| 96 |
+
mode="chunk",
|
| 97 |
+
use_short_conv=True,
|
| 98 |
+
conv_size=config.mem_conv_size,
|
| 99 |
+
conv_bias=config.mem_conv_bias,
|
| 100 |
+
layer_idx=base_attn.layer_idx,
|
| 101 |
+
norm_eps=config.mem_norm_eps,
|
| 102 |
+
)
|
| 103 |
+
# per-forward control, set by LiveMemModel.forward
|
| 104 |
+
self._mem_write_mask: torch.Tensor | None = None
|
| 105 |
+
self._mem_cache = None
|
| 106 |
+
self._mem_use_cache: bool = False
|
| 107 |
+
self._mem_cu_seqlens: torch.Tensor | None = None
|
| 108 |
+
# Training diagnostics. Disabled by default; train/sft/loop.py enables
|
| 109 |
+
# this on one layer so normal forward/inference pays no reduction cost.
|
| 110 |
+
self._record_o_stats: bool = False
|
| 111 |
+
self._last_o_stats: dict[str, torch.Tensor] = {}
|
| 112 |
+
|
| 113 |
+
def forward(
|
| 114 |
+
self,
|
| 115 |
+
hidden_states: torch.Tensor,
|
| 116 |
+
position_embeddings,
|
| 117 |
+
attention_mask: torch.Tensor | None,
|
| 118 |
+
past_key_values: Cache | None = None,
|
| 119 |
+
**kwargs,
|
| 120 |
+
):
|
| 121 |
+
o_main, attn_weights = self.attn(
|
| 122 |
+
hidden_states,
|
| 123 |
+
position_embeddings=position_embeddings,
|
| 124 |
+
attention_mask=attention_mask,
|
| 125 |
+
past_key_values=past_key_values,
|
| 126 |
+
**kwargs,
|
| 127 |
+
)
|
| 128 |
+
o_side, _, _ = self.mem(
|
| 129 |
+
hidden_states,
|
| 130 |
+
write_mask=self._mem_write_mask,
|
| 131 |
+
past_key_values=self._mem_cache,
|
| 132 |
+
use_cache=self._mem_use_cache,
|
| 133 |
+
cu_seqlens=self._mem_cu_seqlens,
|
| 134 |
+
)
|
| 135 |
+
o_total = o_main + o_side
|
| 136 |
+
if self._record_o_stats:
|
| 137 |
+
with torch.no_grad():
|
| 138 |
+
main_abs = o_main.detach().float().abs().mean()
|
| 139 |
+
side_abs = o_side.detach().float().abs().mean()
|
| 140 |
+
total_abs = o_total.detach().float().abs().mean()
|
| 141 |
+
eps = torch.tensor(1e-12, device=total_abs.device, dtype=total_abs.dtype)
|
| 142 |
+
self._last_o_stats = {
|
| 143 |
+
"main_out_abs": main_abs,
|
| 144 |
+
"side_out_abs": side_abs,
|
| 145 |
+
"total_out_abs": total_abs,
|
| 146 |
+
"side_out_ratio": side_abs / torch.maximum(total_abs, eps),
|
| 147 |
+
"side_main_ratio": side_abs / torch.maximum(main_abs, eps),
|
| 148 |
+
}
|
| 149 |
+
return o_total, attn_weights
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
class LiveMemPreTrainedModel(Qwen3PreTrainedModel):
|
| 153 |
+
config: LiveMemConfig
|
| 154 |
+
_no_split_modules = ["Qwen3DecoderLayer"]
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
class LiveMemModel(LiveMemPreTrainedModel, Qwen3Model):
|
| 158 |
+
config_class = LiveMemConfig
|
| 159 |
+
|
| 160 |
+
def __init__(self, config: LiveMemConfig) -> None:
|
| 161 |
+
Qwen3Model.__init__(self, config)
|
| 162 |
+
# Replace self_attn with LiveMemAttention on the selected layers.
|
| 163 |
+
mem_layers = set(config.memory_layer_indices)
|
| 164 |
+
for idx in mem_layers:
|
| 165 |
+
layer = self.layers[idx]
|
| 166 |
+
layer.self_attn = LiveMemAttention(layer.self_attn, config)
|
| 167 |
+
self._mem_layer_indices = sorted(mem_layers)
|
| 168 |
+
self.post_init()
|
| 169 |
+
|
| 170 |
+
def _set_mem_control(self, write_mask, mem_cache, mem_use_cache, cu_seqlens=None) -> None:
|
| 171 |
+
for idx in self._mem_layer_indices:
|
| 172 |
+
m = self.layers[idx].self_attn
|
| 173 |
+
m._mem_write_mask = write_mask
|
| 174 |
+
m._mem_cache = mem_cache
|
| 175 |
+
m._mem_use_cache = mem_use_cache
|
| 176 |
+
m._mem_cu_seqlens = cu_seqlens
|
| 177 |
+
|
| 178 |
+
def _clear_mem_control(self) -> None:
|
| 179 |
+
self._set_mem_control(None, None, False, None)
|
| 180 |
+
|
| 181 |
+
def forward(
|
| 182 |
+
self,
|
| 183 |
+
input_ids: torch.LongTensor | None = None,
|
| 184 |
+
attention_mask: torch.Tensor | None = None,
|
| 185 |
+
position_ids: torch.LongTensor | None = None,
|
| 186 |
+
past_key_values: Cache | None = None,
|
| 187 |
+
inputs_embeds: torch.FloatTensor | None = None,
|
| 188 |
+
use_cache: bool | None = None,
|
| 189 |
+
is_evicted: torch.Tensor | None = None,
|
| 190 |
+
write_mask: torch.Tensor | None = None,
|
| 191 |
+
segment_ids: torch.Tensor | None = None,
|
| 192 |
+
seq_ids: torch.Tensor | None = None,
|
| 193 |
+
chunk_id: torch.Tensor | None = None,
|
| 194 |
+
evict_step: torch.Tensor | None = None,
|
| 195 |
+
cu_seqlens: torch.Tensor | None = None,
|
| 196 |
+
mem_cache=None,
|
| 197 |
+
**kwargs,
|
| 198 |
+
) -> BaseModelOutputWithPast:
|
| 199 |
+
if (input_ids is None) ^ (inputs_embeds is not None):
|
| 200 |
+
raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
|
| 201 |
+
|
| 202 |
+
if inputs_embeds is None:
|
| 203 |
+
inputs_embeds = self.embed_tokens(input_ids)
|
| 204 |
+
|
| 205 |
+
if use_cache and past_key_values is None:
|
| 206 |
+
past_key_values = DynamicCache(config=self.config)
|
| 207 |
+
|
| 208 |
+
if position_ids is None:
|
| 209 |
+
past_seen = past_key_values.get_seq_length() if past_key_values is not None else 0
|
| 210 |
+
position_ids = torch.arange(
|
| 211 |
+
inputs_embeds.shape[1], device=inputs_embeds.device
|
| 212 |
+
).unsqueeze(0) + past_seen
|
| 213 |
+
|
| 214 |
+
# RNN write gate (per token). An explicit `write_mask` always wins (PACK
|
| 215 |
+
# freezes QA segments, segment-write uses 双位置); otherwise Design Y
|
| 216 |
+
# derives it from the eviction layout, and Design X scans continuously.
|
| 217 |
+
if write_mask is not None:
|
| 218 |
+
write_mask = write_mask.to(inputs_embeds.dtype)
|
| 219 |
+
elif is_evicted is not None and self.config.memory_design == "Y":
|
| 220 |
+
write_mask = is_evicted.to(inputs_embeds.dtype)
|
| 221 |
+
|
| 222 |
+
# Build the (eviction / segment / document-aware) causal mask, reused for
|
| 223 |
+
# all layers. `seq_ids` isolates packed sequences (cu_seqlens path);
|
| 224 |
+
# `chunk_id`/`evict_step` drive dynamic chunk eviction (real training).
|
| 225 |
+
if not isinstance(attention_mask, dict):
|
| 226 |
+
and_mask = make_memory_and_mask(is_evicted, segment_ids, seq_ids, chunk_id, evict_step)
|
| 227 |
+
mask_kwargs = {
|
| 228 |
+
"config": self.config,
|
| 229 |
+
"inputs_embeds": inputs_embeds,
|
| 230 |
+
"attention_mask": attention_mask,
|
| 231 |
+
"past_key_values": past_key_values,
|
| 232 |
+
"position_ids": position_ids,
|
| 233 |
+
"and_mask_function": and_mask,
|
| 234 |
+
}
|
| 235 |
+
causal_mask_mapping = {"full_attention": create_causal_mask(**mask_kwargs)}
|
| 236 |
+
if self.has_sliding_layers:
|
| 237 |
+
causal_mask_mapping["sliding_attention"] = create_sliding_window_causal_mask(**mask_kwargs)
|
| 238 |
+
else:
|
| 239 |
+
causal_mask_mapping = attention_mask
|
| 240 |
+
|
| 241 |
+
hidden_states = inputs_embeds
|
| 242 |
+
position_embeddings = self.rotary_emb(hidden_states, position_ids)
|
| 243 |
+
|
| 244 |
+
# Set control on every forward (incl. None when no eviction), so there is
|
| 245 |
+
# no stale state. We deliberately do NOT clear afterwards: gradient
|
| 246 |
+
# checkpointing recomputes this forward during backward and must see the
|
| 247 |
+
# same write_mask. Training is sequential (forward→backward→next forward),
|
| 248 |
+
# so the values stay valid until the next forward overwrites them.
|
| 249 |
+
self._set_mem_control(write_mask, mem_cache, bool(use_cache), cu_seqlens)
|
| 250 |
+
for i, decoder_layer in enumerate(self.layers[: self.config.num_hidden_layers]):
|
| 251 |
+
hidden_states = decoder_layer(
|
| 252 |
+
hidden_states,
|
| 253 |
+
attention_mask=causal_mask_mapping[self.config.layer_types[i]],
|
| 254 |
+
position_embeddings=position_embeddings,
|
| 255 |
+
position_ids=position_ids,
|
| 256 |
+
past_key_values=past_key_values,
|
| 257 |
+
use_cache=use_cache,
|
| 258 |
+
**kwargs,
|
| 259 |
+
)
|
| 260 |
+
|
| 261 |
+
hidden_states = self.norm(hidden_states)
|
| 262 |
+
return BaseModelOutputWithPast(
|
| 263 |
+
last_hidden_state=hidden_states,
|
| 264 |
+
past_key_values=past_key_values if use_cache else None,
|
| 265 |
+
)
|
| 266 |
+
|
| 267 |
+
|
| 268 |
+
class LiveMemForCausalLM(LiveMemPreTrainedModel, Qwen3ForCausalLM):
|
| 269 |
+
config_class = LiveMemConfig
|
| 270 |
+
_tied_weights_keys = {"lm_head.weight": "model.embed_tokens.weight"}
|
| 271 |
+
|
| 272 |
+
def __init__(self, config: LiveMemConfig) -> None:
|
| 273 |
+
# Build directly (don't call Qwen3ForCausalLM.__init__, which would
|
| 274 |
+
# construct a throwaway base Qwen3Model first).
|
| 275 |
+
Qwen3PreTrainedModel.__init__(self, config)
|
| 276 |
+
self.model = LiveMemModel(config)
|
| 277 |
+
self.vocab_size = config.vocab_size
|
| 278 |
+
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
|
| 279 |
+
self.post_init()
|
| 280 |
+
# Honor zero-init of the side o_proj for *both* construction paths
|
| 281 |
+
# (post_init randomizes it, so this must run last). For from_qwen3 the
|
| 282 |
+
# copy-init also zeros it; here it covers from-scratch construction.
|
| 283 |
+
if config.mem_o_proj_zero_init:
|
| 284 |
+
for idx in config.memory_layer_indices:
|
| 285 |
+
nn.init.zeros_(self.model.layers[idx].self_attn.mem.o_proj.weight)
|
| 286 |
+
def forward(
|
| 287 |
+
self,
|
| 288 |
+
input_ids: torch.LongTensor | None = None,
|
| 289 |
+
attention_mask: torch.Tensor | None = None,
|
| 290 |
+
position_ids: torch.LongTensor | None = None,
|
| 291 |
+
past_key_values: Cache | None = None,
|
| 292 |
+
inputs_embeds: torch.FloatTensor | None = None,
|
| 293 |
+
labels: torch.LongTensor | None = None,
|
| 294 |
+
use_cache: bool | None = None,
|
| 295 |
+
is_evicted: torch.Tensor | None = None,
|
| 296 |
+
write_mask: torch.Tensor | None = None,
|
| 297 |
+
segment_ids: torch.Tensor | None = None,
|
| 298 |
+
seq_ids: torch.Tensor | None = None,
|
| 299 |
+
chunk_id: torch.Tensor | None = None,
|
| 300 |
+
evict_step: torch.Tensor | None = None,
|
| 301 |
+
cu_seqlens: torch.Tensor | None = None,
|
| 302 |
+
mem_cache=None,
|
| 303 |
+
logits_to_keep: int | torch.Tensor = 0,
|
| 304 |
+
**kwargs,
|
| 305 |
+
) -> CausalLMOutputWithPast:
|
| 306 |
+
outputs = self.model(
|
| 307 |
+
input_ids=input_ids,
|
| 308 |
+
attention_mask=attention_mask,
|
| 309 |
+
position_ids=position_ids,
|
| 310 |
+
past_key_values=past_key_values,
|
| 311 |
+
inputs_embeds=inputs_embeds,
|
| 312 |
+
use_cache=use_cache,
|
| 313 |
+
is_evicted=is_evicted,
|
| 314 |
+
write_mask=write_mask,
|
| 315 |
+
segment_ids=segment_ids,
|
| 316 |
+
seq_ids=seq_ids,
|
| 317 |
+
chunk_id=chunk_id,
|
| 318 |
+
evict_step=evict_step,
|
| 319 |
+
cu_seqlens=cu_seqlens,
|
| 320 |
+
mem_cache=mem_cache,
|
| 321 |
+
**kwargs,
|
| 322 |
+
)
|
| 323 |
+
hidden_states = outputs.last_hidden_state
|
| 324 |
+
|
| 325 |
+
if labels is not None:
|
| 326 |
+
# Answer-only logits: gather just the supervised positions and run
|
| 327 |
+
# lm_head on those, so we never materialize [B, L, vocab] (≈40GB at
|
| 328 |
+
# L=128k). Mathematically identical to full-seq CE with ignore_index
|
| 329 |
+
# = -100 (mean over answer tokens -> 按 answer token 归一).
|
| 330 |
+
shift_hidden = hidden_states[:, :-1, :]
|
| 331 |
+
shift_labels = labels[:, 1:].to(hidden_states.device)
|
| 332 |
+
sel = shift_labels != -100
|
| 333 |
+
sel_hidden = shift_hidden[sel] # [n_answer, H] bf16
|
| 334 |
+
sel_lab = shift_labels[sel] # [n_answer]
|
| 335 |
+
n = sel_hidden.shape[0]
|
| 336 |
+
# Chunked lm_head + CE over the answer tokens: never materialize the
|
| 337 |
+
# full [n_answer, vocab] fp32 logits (≈30GB when a 64k pack is mostly
|
| 338 |
+
# answer, e.g. long open-ended replies -> OOM). sum/n == mean CE.
|
| 339 |
+
if n == 0:
|
| 340 |
+
loss = hidden_states.sum() * 0.0 # keep graph; no supervised token
|
| 341 |
+
else:
|
| 342 |
+
CH = 8192
|
| 343 |
+
tot = hidden_states.new_zeros((), dtype=torch.float32)
|
| 344 |
+
for s in range(0, n, CH):
|
| 345 |
+
lg = self.lm_head(sel_hidden[s:s + CH]).float()
|
| 346 |
+
tot = tot + nn.functional.cross_entropy(
|
| 347 |
+
lg, sel_lab[s:s + CH], reduction="sum")
|
| 348 |
+
loss = tot / n
|
| 349 |
+
return CausalLMOutputWithPast(loss=loss, logits=None,
|
| 350 |
+
past_key_values=outputs.past_key_values)
|
| 351 |
+
|
| 352 |
+
slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
|
| 353 |
+
logits = self.lm_head(hidden_states[:, slice_indices, :])
|
| 354 |
+
return CausalLMOutputWithPast(
|
| 355 |
+
loss=None,
|
| 356 |
+
logits=logits,
|
| 357 |
+
past_key_values=outputs.past_key_values,
|
| 358 |
+
hidden_states=outputs.last_hidden_state,
|
| 359 |
+
)
|
| 360 |
+
|
| 361 |
+
# ------------------------------------------------------------------ init
|
| 362 |
+
@classmethod
|
| 363 |
+
def from_qwen3(
|
| 364 |
+
cls,
|
| 365 |
+
qwen3_path: str,
|
| 366 |
+
memory_design: str = "Y",
|
| 367 |
+
mem_layers: list[int] | None = None,
|
| 368 |
+
mem_o_proj_zero_init: bool = True,
|
| 369 |
+
dtype: torch.dtype | None = torch.bfloat16,
|
| 370 |
+
device_map: str | None = None,
|
| 371 |
+
attn_implementation: str | None = None,
|
| 372 |
+
**config_overrides,
|
| 373 |
+
) -> "LiveMemForCausalLM":
|
| 374 |
+
"""Build a LiveMem from a pretrained Qwen3: load base weights, then
|
| 375 |
+
copy-init each side branch from the backbone attention geometry."""
|
| 376 |
+
base = Qwen3ForCausalLM.from_pretrained(
|
| 377 |
+
qwen3_path, dtype=dtype, attn_implementation=attn_implementation
|
| 378 |
+
)
|
| 379 |
+
config = LiveMemConfig(
|
| 380 |
+
memory_design=memory_design,
|
| 381 |
+
mem_layers=mem_layers,
|
| 382 |
+
mem_o_proj_zero_init=mem_o_proj_zero_init,
|
| 383 |
+
**{**base.config.to_dict(), **config_overrides},
|
| 384 |
+
)
|
| 385 |
+
if attn_implementation is not None:
|
| 386 |
+
config._attn_implementation = attn_implementation
|
| 387 |
+
|
| 388 |
+
model = cls(config)
|
| 389 |
+
if dtype is not None:
|
| 390 |
+
model = model.to(dtype=dtype)
|
| 391 |
+
|
| 392 |
+
# 1) load all base weights that map directly (embed/mlp/norms/lm_head and,
|
| 393 |
+
# for wrapped layers, the main attention under `.self_attn.attn.*`).
|
| 394 |
+
sd = _remap_base_state_dict(base.state_dict(), config.memory_layer_indices)
|
| 395 |
+
missing, unexpected = model.load_state_dict(sd, strict=False)
|
| 396 |
+
# side-branch params (model.layers.*.self_attn.mem.*) are expected-missing
|
| 397 |
+
leftover = [k for k in missing if ".self_attn.mem." not in k]
|
| 398 |
+
if leftover:
|
| 399 |
+
raise RuntimeError(f"Unexpected missing keys after base load: {leftover[:8]} ...")
|
| 400 |
+
if unexpected:
|
| 401 |
+
raise RuntimeError(f"Unexpected keys when loading base: {unexpected[:8]} ...")
|
| 402 |
+
|
| 403 |
+
# 2) copy-init each side branch from its (now-loaded) main attention.
|
| 404 |
+
for idx in config.memory_layer_indices:
|
| 405 |
+
mattn = model.model.layers[idx].self_attn
|
| 406 |
+
copy_init_side_branch(mattn.mem, mattn.attn, config.mem_o_proj_zero_init)
|
| 407 |
+
|
| 408 |
+
del base
|
| 409 |
+
if device_map is not None:
|
| 410 |
+
model = model.to(device_map)
|
| 411 |
+
return model
|
| 412 |
+
|
| 413 |
+
|
| 414 |
+
def _remap_base_state_dict(state_dict: dict, mem_layers: list[int]) -> dict:
|
| 415 |
+
"""Insert `.attn` into self_attn keys for wrapped layers so base attention
|
| 416 |
+
weights land on LiveMemAttention.attn.*; all other keys pass through."""
|
| 417 |
+
mem_set = set(mem_layers)
|
| 418 |
+
sub = ("q_proj", "k_proj", "v_proj", "o_proj", "q_norm", "k_norm")
|
| 419 |
+
out = {}
|
| 420 |
+
for k, v in state_dict.items():
|
| 421 |
+
nk = k
|
| 422 |
+
if ".self_attn." in k:
|
| 423 |
+
parts = k.split(".")
|
| 424 |
+
try:
|
| 425 |
+
li = parts.index("layers")
|
| 426 |
+
layer_idx = int(parts[li + 1])
|
| 427 |
+
except (ValueError, IndexError):
|
| 428 |
+
layer_idx = None
|
| 429 |
+
if layer_idx in mem_set and any(f".self_attn.{s}." in k for s in sub):
|
| 430 |
+
nk = k.replace(".self_attn.", ".self_attn.attn.", 1)
|
| 431 |
+
out[nk] = v
|
| 432 |
+
return out
|
| 433 |
+
|
| 434 |
+
|
| 435 |
+
@torch.no_grad()
|
| 436 |
+
def copy_init_side_branch(
|
| 437 |
+
side: LiveMemGatedDeltaNet2, attn: Qwen3Attention, zero_o: bool
|
| 438 |
+
) -> None:
|
| 439 |
+
"""Copy Qwen3 QKVO into the GDN2 side branch.
|
| 440 |
+
|
| 441 |
+
Supports both the legacy full-MHA side branch (32 Q/K/V heads for Qwen3-4B)
|
| 442 |
+
and the compact KV-head branch (8 Q/K/V heads + expanded V):
|
| 443 |
+
- Q: direct copy if head counts match; if target heads match backbone KV
|
| 444 |
+
heads, average the corresponding GQA Q group.
|
| 445 |
+
- K: copy/adapt from backbone KV heads.
|
| 446 |
+
- V: copy/adapt from backbone KV heads, then block-repeat each V head along
|
| 447 |
+
its channel dimension when `expand_v > 1`.
|
| 448 |
+
- O: copied only when shapes match; normally zero-initialized for training.
|
| 449 |
+
"""
|
| 450 |
+
hd = attn.head_dim
|
| 451 |
+
dt = side.q_proj.weight.dtype
|
| 452 |
+
qh = attn.q_proj.weight.shape[0] // hd
|
| 453 |
+
kvh = attn.k_proj.weight.shape[0] // hd
|
| 454 |
+
|
| 455 |
+
def adapt_heads(heads: torch.Tensor, target_heads: int, name: str) -> torch.Tensor:
|
| 456 |
+
src_heads = heads.shape[0]
|
| 457 |
+
if target_heads == src_heads:
|
| 458 |
+
return heads
|
| 459 |
+
if target_heads > src_heads and target_heads % src_heads == 0:
|
| 460 |
+
return heads.repeat_interleave(target_heads // src_heads, dim=0)
|
| 461 |
+
if src_heads > target_heads and src_heads % target_heads == 0:
|
| 462 |
+
return heads.view(target_heads, src_heads // target_heads, hd, -1).mean(dim=1)
|
| 463 |
+
raise ValueError(f"cannot adapt {name} heads from {src_heads} to {target_heads}")
|
| 464 |
+
|
| 465 |
+
q_heads = attn.q_proj.weight.view(qh, hd, -1)
|
| 466 |
+
if side.num_heads == qh:
|
| 467 |
+
q_init = q_heads
|
| 468 |
+
elif qh % kvh == 0 and side.num_heads == kvh:
|
| 469 |
+
q_init = q_heads.view(kvh, qh // kvh, hd, -1).mean(dim=1)
|
| 470 |
+
else:
|
| 471 |
+
q_init = adapt_heads(q_heads, side.num_heads, "q")
|
| 472 |
+
side.q_proj.weight.copy_(q_init.reshape(side.q_proj.weight.shape).to(dt))
|
| 473 |
+
|
| 474 |
+
k_heads = attn.k_proj.weight.view(kvh, hd, -1)
|
| 475 |
+
k_init = adapt_heads(k_heads, side.num_heads, "k")
|
| 476 |
+
side.k_proj.weight.copy_(k_init.reshape(side.k_proj.weight.shape).to(dt))
|
| 477 |
+
|
| 478 |
+
v_heads = adapt_heads(attn.v_proj.weight.view(kvh, hd, -1), side.num_v_heads, "v")
|
| 479 |
+
if side.head_v_dim % hd != 0:
|
| 480 |
+
raise ValueError(
|
| 481 |
+
f"side.head_v_dim={side.head_v_dim} must be a multiple of backbone head_dim={hd} "
|
| 482 |
+
"for copy initialization"
|
| 483 |
+
)
|
| 484 |
+
v_expand = side.head_v_dim // hd
|
| 485 |
+
v_init = v_heads.repeat(1, v_expand, 1)
|
| 486 |
+
side.v_proj.weight.copy_(v_init.reshape(side.v_proj.weight.shape).to(dt))
|
| 487 |
+
|
| 488 |
+
if zero_o:
|
| 489 |
+
side.o_proj.weight.zero_()
|
| 490 |
+
else:
|
| 491 |
+
if side.o_proj.weight.shape != attn.o_proj.weight.shape:
|
| 492 |
+
raise ValueError(
|
| 493 |
+
f"cannot copy-init o_proj with shape {tuple(side.o_proj.weight.shape)} "
|
| 494 |
+
f"from backbone shape {tuple(attn.o_proj.weight.shape)}; use zero_o=True"
|
| 495 |
+
)
|
| 496 |
+
side.o_proj.weight.copy_(attn.o_proj.weight.to(side.o_proj.weight.dtype))
|
modeling_livemem_gdn2.py
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""GDN2 memory side-branch with an optional per-token write gate.
|
| 2 |
+
|
| 3 |
+
This subclasses fla's `GatedDeltaNet2` and overrides `forward` to apply a
|
| 4 |
+
`write_mask` that freezes the recurrence on read tokens. The GDN-2 update is
|
| 5 |
+
|
| 6 |
+
S_t = (I - k_t (b_t * k_t)^T) Diag(exp(g_t)) S_{t-1} + k_t (w_t * v_t)^T
|
| 7 |
+
|
| 8 |
+
so setting g_t = b_t = w_t = 0 gives S_t = S_{t-1} (read-only); the output
|
| 9 |
+
o_t = q_t · S_t is still produced (the token reads the memory). Verified
|
| 10 |
+
against `fla.ops.gdn2.naive.naive_recurrent_gdn2`.
|
| 11 |
+
|
| 12 |
+
- Design Y: write_mask = is_evicted (open the gate only on the compress/evict
|
| 13 |
+
region; live + Q + A are frozen read-only).
|
| 14 |
+
- Design X: write_mask = None -> standard continuous scan over all tokens.
|
| 15 |
+
"""
|
| 16 |
+
from __future__ import annotations
|
| 17 |
+
|
| 18 |
+
import torch
|
| 19 |
+
import torch.nn.functional as F
|
| 20 |
+
from einops import rearrange, repeat
|
| 21 |
+
|
| 22 |
+
from fla.layers.gdn2 import GatedDeltaNet2
|
| 23 |
+
from fla.layers.utils import (
|
| 24 |
+
get_layer_cache,
|
| 25 |
+
get_unpad_data,
|
| 26 |
+
index_first_axis,
|
| 27 |
+
pad_input,
|
| 28 |
+
update_layer_cache,
|
| 29 |
+
)
|
| 30 |
+
from fla.ops.gdn2 import chunk_gdn2, fused_recurrent_gdn2
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
class LiveMemGatedDeltaNet2(GatedDeltaNet2):
|
| 34 |
+
def forward(
|
| 35 |
+
self,
|
| 36 |
+
hidden_states: torch.Tensor,
|
| 37 |
+
write_mask: torch.Tensor | None = None,
|
| 38 |
+
attention_mask: torch.Tensor | None = None,
|
| 39 |
+
past_key_values=None,
|
| 40 |
+
use_cache: bool | None = False,
|
| 41 |
+
output_attentions: bool | None = False,
|
| 42 |
+
**kwargs,
|
| 43 |
+
):
|
| 44 |
+
"""Mirrors fla.GatedDeltaNet2.forward, adding `write_mask` support.
|
| 45 |
+
|
| 46 |
+
`write_mask`: float/bool [batch, seq_len]; 0 freezes the recurrence
|
| 47 |
+
(g=b=w=0 -> S_t = S_{t-1}). Padding (`attention_mask`) + `write_mask`
|
| 48 |
+
together are not supported (the unpad reorder would desync the mask);
|
| 49 |
+
the training path always passes `attention_mask=None`.
|
| 50 |
+
"""
|
| 51 |
+
if attention_mask is not None:
|
| 52 |
+
assert len(attention_mask.shape) == 2, (
|
| 53 |
+
"Expected attention_mask as a [batch_size, seq_len] 0/1 padding mask."
|
| 54 |
+
)
|
| 55 |
+
assert write_mask is None, (
|
| 56 |
+
"write_mask is incompatible with a 2D padding mask (unpad reorder)."
|
| 57 |
+
)
|
| 58 |
+
|
| 59 |
+
cu_seqlens = kwargs.get("cu_seqlens")
|
| 60 |
+
batch_size, q_len, _ = hidden_states.shape
|
| 61 |
+
if cu_seqlens is not None and cu_seqlens.ndim == 2:
|
| 62 |
+
if use_cache:
|
| 63 |
+
raise ValueError("batched cu_seqlens training path does not support cache")
|
| 64 |
+
outs = []
|
| 65 |
+
for b in range(batch_size):
|
| 66 |
+
cu = cu_seqlens[b]
|
| 67 |
+
cu = cu[cu >= 0].contiguous()
|
| 68 |
+
wm = write_mask[b:b + 1] if write_mask is not None else None
|
| 69 |
+
o, _, _ = self.forward(
|
| 70 |
+
hidden_states[b:b + 1],
|
| 71 |
+
write_mask=wm,
|
| 72 |
+
attention_mask=None,
|
| 73 |
+
past_key_values=None,
|
| 74 |
+
use_cache=False,
|
| 75 |
+
output_attentions=output_attentions,
|
| 76 |
+
cu_seqlens=cu,
|
| 77 |
+
)
|
| 78 |
+
outs.append(o)
|
| 79 |
+
return torch.cat(outs, dim=0), None, past_key_values
|
| 80 |
+
|
| 81 |
+
mode = "fused_recurrent" if (q_len <= 64 and not self.training) else self.mode
|
| 82 |
+
if self.training:
|
| 83 |
+
assert mode == "chunk", "Only chunk mode is supported in training."
|
| 84 |
+
|
| 85 |
+
last_state = get_layer_cache(self, past_key_values)
|
| 86 |
+
indices = None
|
| 87 |
+
if cu_seqlens is None and attention_mask is not None:
|
| 88 |
+
indices, cu_seqlens, _ = get_unpad_data(attention_mask[:, -q_len:])
|
| 89 |
+
hidden_states = index_first_axis(
|
| 90 |
+
rearrange(hidden_states, "b s ... -> (b s) ..."), indices
|
| 91 |
+
).unsqueeze(0)
|
| 92 |
+
|
| 93 |
+
if self.use_short_conv:
|
| 94 |
+
conv_state_q, conv_state_k, conv_state_v = None, None, None
|
| 95 |
+
if last_state is not None:
|
| 96 |
+
conv_state_q, conv_state_k, conv_state_v = last_state["conv_state"]
|
| 97 |
+
q, conv_state_q = self.q_conv1d(
|
| 98 |
+
x=self.q_proj(hidden_states), cache=conv_state_q,
|
| 99 |
+
output_final_state=use_cache, cu_seqlens=cu_seqlens,
|
| 100 |
+
)
|
| 101 |
+
k, conv_state_k = self.k_conv1d(
|
| 102 |
+
x=self.k_proj(hidden_states), cache=conv_state_k,
|
| 103 |
+
output_final_state=use_cache, cu_seqlens=cu_seqlens,
|
| 104 |
+
)
|
| 105 |
+
v, conv_state_v = self.v_conv1d(
|
| 106 |
+
x=self.v_proj(hidden_states), cache=conv_state_v,
|
| 107 |
+
output_final_state=use_cache, cu_seqlens=cu_seqlens,
|
| 108 |
+
)
|
| 109 |
+
else:
|
| 110 |
+
q = F.silu(self.q_proj(hidden_states))
|
| 111 |
+
k = F.silu(self.k_proj(hidden_states))
|
| 112 |
+
v = F.silu(self.v_proj(hidden_states))
|
| 113 |
+
|
| 114 |
+
g = F.softplus(self.f_proj(hidden_states).float() + self.dt_bias)
|
| 115 |
+
b = self.b_proj(hidden_states).sigmoid()
|
| 116 |
+
w = self.w_proj(hidden_states).sigmoid()
|
| 117 |
+
|
| 118 |
+
q, k, g = (rearrange(x, "... (h d) -> ... h d", d=self.head_k_dim) for x in (q, k, g))
|
| 119 |
+
v = rearrange(v, "... (h d) -> ... h d", d=self.head_v_dim)
|
| 120 |
+
b = rearrange(b, "... (h d) -> ... h d", d=self.head_k_dim)
|
| 121 |
+
w = rearrange(w, "... (h d) -> ... h d", d=self.head_v_dim)
|
| 122 |
+
g = -self.A_log.float().exp().unsqueeze(-1) * g
|
| 123 |
+
|
| 124 |
+
# --- write gate (the only addition over fla) -----------------------
|
| 125 |
+
# Zeroing g/b/w on read tokens freezes the state at S_{t-1}.
|
| 126 |
+
if write_mask is not None:
|
| 127 |
+
wm = write_mask.to(g.dtype).view(write_mask.shape[0], write_mask.shape[1], 1, 1)
|
| 128 |
+
g = g * wm
|
| 129 |
+
b = b * wm.to(b.dtype)
|
| 130 |
+
w = w * wm.to(w.dtype)
|
| 131 |
+
# -------------------------------------------------------------------
|
| 132 |
+
|
| 133 |
+
if self.num_v_heads > self.num_heads:
|
| 134 |
+
q, k, g, b = (
|
| 135 |
+
repeat(x, "... h d -> ... (h g) d", g=self.num_v_heads // self.num_heads)
|
| 136 |
+
for x in (q, k, g, b)
|
| 137 |
+
)
|
| 138 |
+
|
| 139 |
+
if self.allow_neg_eigval:
|
| 140 |
+
b = b * 2.0
|
| 141 |
+
|
| 142 |
+
recurrent_state = last_state["recurrent_state"] if last_state is not None else None
|
| 143 |
+
if mode == "chunk":
|
| 144 |
+
o, recurrent_state = chunk_gdn2(
|
| 145 |
+
q=q, k=k, v=v, g=g, b=b, w=w,
|
| 146 |
+
initial_state=recurrent_state, output_final_state=use_cache,
|
| 147 |
+
use_qk_l2norm_in_kernel=True, cu_seqlens=cu_seqlens,
|
| 148 |
+
)
|
| 149 |
+
elif mode == "fused_recurrent":
|
| 150 |
+
o, recurrent_state = fused_recurrent_gdn2(
|
| 151 |
+
q=q, k=k, v=v, g=g, b=b, w=w,
|
| 152 |
+
initial_state=recurrent_state, output_final_state=use_cache,
|
| 153 |
+
use_qk_l2norm_in_kernel=True, cu_seqlens=cu_seqlens,
|
| 154 |
+
)
|
| 155 |
+
else:
|
| 156 |
+
raise NotImplementedError(f"Unsupported mode `{mode}`.")
|
| 157 |
+
|
| 158 |
+
update_layer_cache(
|
| 159 |
+
self, past_key_values,
|
| 160 |
+
recurrent_state=recurrent_state,
|
| 161 |
+
conv_state=(conv_state_q, conv_state_k, conv_state_v) if self.use_short_conv else None,
|
| 162 |
+
offset=q_len,
|
| 163 |
+
)
|
| 164 |
+
|
| 165 |
+
o = self.o_norm(o, rearrange(self.g_proj(hidden_states), "... (h d) -> ... h d", d=self.head_v_dim))
|
| 166 |
+
o = rearrange(o, "b t h d -> b t (h d)")
|
| 167 |
+
o = self.o_proj(o)
|
| 168 |
+
if attention_mask is not None:
|
| 169 |
+
o = pad_input(o.squeeze(0), indices, batch_size, q_len)
|
| 170 |
+
|
| 171 |
+
return o, None, past_key_values
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch>=2.7.0
|
| 2 |
+
transformers>=5.12.1
|
| 3 |
+
einops>=0.8.0
|
| 4 |
+
flash-linear-attention[cuda]>=0.5.1
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"local_files_only": false,
|
| 24 |
+
"model_max_length": 262144,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|