Upload 4 files
Browse files
LICENSE
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
NOTICE
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
TensorPEFT
|
| 2 |
+
Copyright 2026 Angshul Majumdar
|
| 3 |
+
|
| 4 |
+
Licensed under the Apache License, Version 2.0 (see LICENSE).
|
README.md
CHANGED
|
@@ -1,3 +1,149 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# TensorPEFT
|
| 2 |
+
|
| 3 |
+
Parameter-efficient fine-tuning with **tensor gradient-pursuit adapters**. TensorPEFT is a drop-in
|
| 4 |
+
alternative to LoRA for Hugging Face models, designed for very small trainable-parameter budgets.
|
| 5 |
+
|
| 6 |
+
LoRA gives every weight matrix its own low-rank update. TensorPEFT instead stacks all
|
| 7 |
+
equal-shaped matrices of the network into one tensor, for example
|
| 8 |
+
`layers x {q,k,v,o} x d_in x d_out`, and learns a few **rank-one CP atoms** of that tensor:
|
| 9 |
+
|
| 10 |
+
dW = sum_i a_i u_i(layer) o u_i(role) o u_i(in) o u_i(out)
|
| 11 |
+
|
| 12 |
+
Each atom couples every layer and projection while costing only
|
| 13 |
+
`L + P + d_in + d_out + 1` parameters. The atoms are not random. They are the leading rank-one
|
| 14 |
+
CP components of the negative gradient tensor (higher-order power iteration with deflation),
|
| 15 |
+
computed from **one gradient probe** before training. The coefficients start at zero, so the
|
| 16 |
+
model is unchanged at step 0, and every atom starts on a steepest-descent direction. After that,
|
| 17 |
+
training is ordinary: any optimiser and the HF `Trainer` both work.
|
| 18 |
+
|
| 19 |
+
## Install
|
| 20 |
+
|
| 21 |
+
pip install tensorpeft # once published; until then: pip install .
|
| 22 |
+
|
| 23 |
+
It requires `torch>=2.1`, `transformers>=4.40`, `safetensors` and `huggingface_hub`.
|
| 24 |
+
|
| 25 |
+
## Quick start
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
from transformers import AutoModelForCausalLM
|
| 29 |
+
from tensorpeft import TensorPEFTConfig, get_tensorpeft_model, TensorPEFTModel
|
| 30 |
+
|
| 31 |
+
base = AutoModelForCausalLM.from_pretrained("gpt2")
|
| 32 |
+
model = get_tensorpeft_model(base, TensorPEFTConfig(atoms_per_group=4))
|
| 33 |
+
|
| 34 |
+
model.init_atoms(train_dataloader, n_batches=4) # the one step LoRA does not have
|
| 35 |
+
model.print_trainable_parameters() # trainable params: 37,036 || ... || 0.0298%
|
| 36 |
+
|
| 37 |
+
# train as usual: AdamW, lr ~3e-3, short warm-up, weight_decay 0 (or TensorPEFTTrainer below)
|
| 38 |
+
|
| 39 |
+
model.save_pretrained("my-adapter") # adapter_config.json + adapter_model.safetensors
|
| 40 |
+
model.push_to_hub("your-name/my-adapter")
|
| 41 |
+
|
| 42 |
+
base = AutoModelForCausalLM.from_pretrained("gpt2")
|
| 43 |
+
model = TensorPEFTModel.from_pretrained(base, "your-name/my-adapter") # local dir or Hub id
|
| 44 |
+
merged = model.merge_and_unload() # plain HF model, zero inference overhead
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
`train_dataloader` can yield dicts (`input_ids`, optional `attention_mask` / `labels`) or plain
|
| 48 |
+
input-id tensors. For causal LMs, labels default to the inputs.
|
| 49 |
+
|
| 50 |
+
### With the Hugging Face Trainer
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
from tensorpeft import TensorPEFTTrainer
|
| 54 |
+
trainer = TensorPEFTTrainer(model=model, args=training_args, train_dataset=ds, data_collator=collator)
|
| 55 |
+
trainer.train() # checkpoints contain only the adapter
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
`TensorPEFTTrainer` is the stock `Trainer` except that it saves adapters instead of full model
|
| 59 |
+
weights. A complete script is in `examples/train_with_trainer.py`.
|
| 60 |
+
|
| 61 |
+
## Configuration
|
| 62 |
+
|
| 63 |
+
| `TensorPEFTConfig` field | default | meaning |
|
| 64 |
+
|---|---|---|
|
| 65 |
+
| `atoms_per_group` | 4 | rank-one atoms per tensor group; this sets the budget |
|
| 66 |
+
| `target_modules` | `"all-linear"` | or a list of name suffixes, e.g. `["q_proj", "v_proj"]` (`"c_attn.q"` for GPT-2) |
|
| 67 |
+
| `exclude_modules` | `lm_head`, embeddings | never adapted |
|
| 68 |
+
| `split_fused_qkv` | True | split GPT-2's fused `c_attn` into q, k and v |
|
| 69 |
+
| `init_batches` | 4 | batches used by `init_atoms` |
|
| 70 |
+
| `hopm_iters` | 30 | power-iteration sweeps per atom |
|
| 71 |
+
| `alpha_scale` | 33.3 | coefficient reparametrisation so that one learning rate (~3e-3) fits coefficients and factors |
|
| 72 |
+
|
| 73 |
+
**Budget.** Groups are formed automatically by matrix shape. GPT-2 small has three groups:
|
| 74 |
+
`{q,k,v,o}` (12x4x768x768), MLP-in (12x768x3072) and MLP-out (12x3072x768). One atom per group
|
| 75 |
+
is 9,259 parameters, four per group is 37,036, and six per group is 55,554.
|
| 76 |
+
`print_trainable_parameters()` shows the exact count for any model.
|
| 77 |
+
|
| 78 |
+
**Recipe.** Use AdamW at lr 3e-3 with about 10 warm-up steps, then a constant schedule and
|
| 79 |
+
weight decay 0. Use all atoms from the start: adding atoms gradually during training was clearly
|
| 80 |
+
worse in our tests.
|
| 81 |
+
|
| 82 |
+
## Results
|
| 83 |
+
|
| 84 |
+
Setup: GPT-2 124M (English base) fine-tuned on Bengali news (3M tokens), 300 AdamW steps,
|
| 85 |
+
batch 8 x 128 tokens. Validation cross-entropy is in nats/token, lower is better; the base model
|
| 86 |
+
scores 1.708. All methods saw identical data, and baseline learning rates follow their papers.
|
| 87 |
+
|
| 88 |
+
Three seeds, best baseline per budget:
|
| 89 |
+
|
| 90 |
+
| budget | TensorPEFT | best baseline | difference | seeds won | p (paired t) |
|
| 91 |
+
|---|---:|---|---:|:---:|---:|
|
| 92 |
+
| ~9k params | **1.3245 ± 0.004** | prompt tuning: 1.3684 ± 0.010 | **-0.044** | 3/3 | 0.008 |
|
| 93 |
+
| ~37k | 1.2558 ± 0.010 | LayerNorm tuning (38.4k): 1.2504 ± 0.003 | +0.005 | 1/3 | 0.37 (tie) |
|
| 94 |
+
| ~55k | **1.2368 ± 0.017** | (IA)³: 1.2880 ± 0.003 | **-0.051** | 3/3 | 0.026 |
|
| 95 |
+
|
| 96 |
+
All baselines at each budget (seed 0):
|
| 97 |
+
|
| 98 |
+
| budget | TensorPEFT | LoRA | QLoRA | VeRA | (IA)³ | prompt tuning | LayerNorm tuning | BitFit |
|
| 99 |
+
|---|---:|---:|---:|---:|---:|---:|---:|---:|
|
| 100 |
+
| ~1.5k | **1.461** | - | - | - | - | 1.493 (768 params) | 1.600 | - |
|
| 101 |
+
| ~9k | **1.327** | 1.430 | - | - | 1.432 | 1.370 | 1.407 | - |
|
| 102 |
+
| ~37k | 1.255 | 1.318 | 1.335 | 1.393 (24.6k) | - | 1.327 | **1.253** | - |
|
| 103 |
+
| ~55k | **1.231** | - | - | - | 1.289 | - | - | - |
|
| 104 |
+
| ~83k | - | - | - | - | - | - | - | 1.326 |
|
| 105 |
+
|
| 106 |
+
TensorPEFT budgets map to configs as follows: ~1.5k is one atom on the attention tensor only
|
| 107 |
+
(`target_modules=["c_attn.q", "c_attn.k", "c_attn.v", "attn.c_proj"]`, `atoms_per_group=1`),
|
| 108 |
+
~9k is `atoms_per_group=1`, ~37k is 4 and ~55k is 6. A dash means the method cannot be
|
| 109 |
+
configured at that budget on GPT-2, or was not run there.
|
| 110 |
+
LoRA's smallest all-layer configuration is r=1 on q,v (37k parameters). At 9k it is LoRA r=1 on
|
| 111 |
+
q,v of the last 3 layers.
|
| 112 |
+
|
| 113 |
+
**What this does and does not show.** TensorPEFT beats every baseline from about 1.5k to
|
| 114 |
+
about 9k parameters and at about 55k, and ties LayerNorm tuning at about 37k. With larger
|
| 115 |
+
budgets (≥ 115k) LoRA was better in our tests. The evidence covers one base model, one task and
|
| 116 |
+
short training. Results on other models and downstream tasks are not yet available.
|
| 117 |
+
|
| 118 |
+
`examples/reproduce_gpt2_bengali.py` reruns these benchmarks with this package
|
| 119 |
+
(`--atoms-per-group 1 | 4 | 6`). The
|
| 120 |
+
data comes from the Bengali news corpus at github.com/soham96/Bengali_news_classifier,
|
| 121 |
+
tokenised with the GPT-2 tokenizer.
|
| 122 |
+
|
| 123 |
+
## Supported models
|
| 124 |
+
|
| 125 |
+
Any model whose transformer blocks use `nn.Linear` or GPT-2-style `Conv1D` layers inside
|
| 126 |
+
numbered blocks (`...layers.N...` / `...h.N...`). Tested on GPT-2, Llama (GQA), Qwen2, Mistral,
|
| 127 |
+
Phi and Gemma configurations. Fused projections other than GPT-2's `c_attn` are treated as a
|
| 128 |
+
single matrix.
|
| 129 |
+
|
| 130 |
+
## Limitations (v0.1)
|
| 131 |
+
|
| 132 |
+
- **GPU support is untested.** The code is device- and dtype-agnostic (adapter parameters in
|
| 133 |
+
fp32, bf16/fp16 bases supported), but all tests and benchmarks so far ran on CPU.
|
| 134 |
+
- **Probe memory.** `init_atoms` needs one backward pass with gradients on the targeted weights,
|
| 135 |
+
plus an fp32 copy of each group's gradient tensor. That is roughly 2x the size of the targeted
|
| 136 |
+
weights, temporarily. Use `target_modules` to limit it for large models.
|
| 137 |
+
- **Quantised bases** (bitsandbytes 4/8-bit) are not supported yet, because the probe needs
|
| 138 |
+
weight gradients.
|
| 139 |
+
- **No checkpoint resume.** `Trainer` resume-from-checkpoint is not implemented; reload with
|
| 140 |
+
`TensorPEFTModel.from_pretrained(..., is_trainable=True)`.
|
| 141 |
+
|
| 142 |
+
## Tests
|
| 143 |
+
|
| 144 |
+
pip install .[test]
|
| 145 |
+
pytest tests
|
| 146 |
+
|
| 147 |
+
## License
|
| 148 |
+
|
| 149 |
+
Apache-2.0. Copyright 2026 Angshul Majumdar.
|
pyproject.toml
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[build-system]
|
| 2 |
+
requires = ["setuptools>=64", "wheel"]
|
| 3 |
+
build-backend = "setuptools.build_meta"
|
| 4 |
+
|
| 5 |
+
[project]
|
| 6 |
+
name = "tensorpeft"
|
| 7 |
+
version = "0.1.0"
|
| 8 |
+
description = "Parameter-efficient fine-tuning with tensor gradient-pursuit (rank-one CP) adapters"
|
| 9 |
+
readme = "README.md"
|
| 10 |
+
license = "Apache-2.0"
|
| 11 |
+
license-files = ["LICENSE", "NOTICE"]
|
| 12 |
+
authors = [{ name = "Angshul Majumdar", email = "angshul@iiitd.ac.in" }]
|
| 13 |
+
requires-python = ">=3.9"
|
| 14 |
+
dependencies = [
|
| 15 |
+
"torch>=2.1",
|
| 16 |
+
"transformers>=4.40",
|
| 17 |
+
"safetensors>=0.4",
|
| 18 |
+
"huggingface_hub>=0.20",
|
| 19 |
+
]
|
| 20 |
+
keywords = ["peft", "fine-tuning", "lora", "tensor", "transformers", "huggingface"]
|
| 21 |
+
classifiers = [
|
| 22 |
+
"Programming Language :: Python :: 3",
|
| 23 |
+
"Intended Audience :: Science/Research",
|
| 24 |
+
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
| 25 |
+
]
|
| 26 |
+
|
| 27 |
+
[project.optional-dependencies]
|
| 28 |
+
test = ["pytest", "accelerate"]
|
| 29 |
+
|
| 30 |
+
[tool.setuptools.packages.find]
|
| 31 |
+
where = ["src"]
|