初始化项目，由ModelHub XC社区提供模型
Model: Polygl0t/Tucano2-qwen-3.7B-Base Source: Original Platform
This commit is contained in:
ModelHub XC
52
.gitattributes
vendored
Normal file
52
.gitattributes
vendored
Normal file
@@ -0,0 +1,52 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
logo.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/arc_challenge.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/before_and_after.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/belebele.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/bluex.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/calame.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/enem.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/global_piqa.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/gradient_norm.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/hellaswag.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/lambada.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/learning_curve.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/mmlu.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/npm_easy.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/npm_hard.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/oab.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/performance_vs_compute.png filter=lfs diff=lfs merge=lfs -text
|
||||
3
.plots/arc_challenge.png
Normal file
3
.plots/arc_challenge.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8af866351e9918524decc2b6c89b2d42bc1a512a6c9b01939b1135d4624b8ea
|
||||
size 195444
|
||||
3
.plots/before_and_after.png
Normal file
3
.plots/before_and_after.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9329d9b9e44be3dc8e30d5b1d63e045e82416dfe0497e71c50889411f47415c3
|
||||
size 278984
|
||||
3
.plots/belebele.png
Normal file
3
.plots/belebele.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13a715235191f3c7e63e65e35a317337a23ceebf01d0ca1d0a988b6e72f0d688
|
||||
size 194551
|
||||
3
.plots/bluex.png
Normal file
3
.plots/bluex.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:359efe6b2879ac4bde29d1924dc9a7fa554d5a07ec13821b145718d55a2fbf9d
|
||||
size 189109
|
||||
3
.plots/calame.png
Normal file
3
.plots/calame.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eee7333dd48cda9a8754942803f5a35a4555d7d8c6d1866a39a0cfb81c7a11fa
|
||||
size 174470
|
||||
3
.plots/enem.png
Normal file
3
.plots/enem.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4dd7c49b0fee952386f5be0aeae54cfd91eddd53f29466981ab8bbe2ef73f4b7
|
||||
size 163967
|
||||
3
.plots/global_piqa.png
Normal file
3
.plots/global_piqa.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:177b7cca833de2440787821ffd7aa92525d5955dc28c07fc9b7e803afacea56e
|
||||
size 166269
|
||||
3
.plots/gradient_norm.png
Normal file
3
.plots/gradient_norm.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aab0537cf6a04037928d0ebaa88ab2e84a23c0d869cb0f32bd0c7fd9014f7f9a
|
||||
size 273517
|
||||
3
.plots/hellaswag.png
Normal file
3
.plots/hellaswag.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b6a6d0ecb3ef72c2afd1c828e075f16b0cfb365f335007f4bfc8323c9117b52
|
||||
size 168704
|
||||
3
.plots/lambada.png
Normal file
3
.plots/lambada.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8079bd87390d73ee8c40ad849ab1f89e35f95bc29af78fcabd025a5b10ff0eac
|
||||
size 180169
|
||||
3
.plots/learning_curve.png
Normal file
3
.plots/learning_curve.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0cf6807d2ef3dbbb0b332ff6f08e2cfef52cfbe9936b43bfa0a973e751b94068
|
||||
size 221929
|
||||
3
.plots/mmlu.png
Normal file
3
.plots/mmlu.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ef96236e6f0c577dea8fc3b3dfa2739061d7fc6ce1e9a02e51453d8ae62543c4
|
||||
size 181825
|
||||
3
.plots/npm_easy.png
Normal file
3
.plots/npm_easy.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b83aac4bb477232ed43a9a0af497967d3e3e041ee515b72d5fdc310833881039
|
||||
size 188554
|
||||
3
.plots/npm_hard.png
Normal file
3
.plots/npm_hard.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f416e9e8d05808313600b206ab53c612c90b2be8325f87b28c5fb8b812066699
|
||||
size 190920
|
||||
3
.plots/oab.png
Normal file
3
.plots/oab.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e3e05da44c8ec4e744e6d51b00cd32ff48dfaf94a5036d5498c4fe8a8e9417e
|
||||
size 191665
|
||||
3
.plots/performance_vs_compute.png
Normal file
3
.plots/performance_vs_compute.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4a657d6d68d6f2f1fbf0d3750eac546a7ead054995a466497e0e31bfeedd49c
|
||||
size 949327
|
||||
190
LICENSE
Normal file
190
LICENSE
Normal file
@@ -0,0 +1,190 @@
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
Copyright Nicholas Kluge Corrêa, Shiza Fatimah, Aniket Sen, and Sophia Falk
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
495
README.md
Normal file
495
README.md
Normal file
@@ -0,0 +1,495 @@
|
||||
---
|
||||
language:
|
||||
- pt
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- text-generation-inference
|
||||
datasets:
|
||||
- Polygl0t/gigaverbo-v2
|
||||
- Polygl0t/gigaverbo-v2-synth
|
||||
metrics:
|
||||
- perplexity
|
||||
pipeline_tag: text-generation
|
||||
widget:
|
||||
- text: "A floresta da Amazônia é conhecida por sua"
|
||||
example_title: Exemplo
|
||||
- text: "Uma das coisas que Portugal, Angola, Brasil e Moçambique tem em comum é o"
|
||||
example_title: Exemplo
|
||||
- text: "O Carnaval do Rio de Janeiro é"
|
||||
example_title: Exemplo
|
||||
inference:
|
||||
parameters:
|
||||
repetition_penalty: 1.2
|
||||
temperature: 0.1
|
||||
top_k: 50
|
||||
top_p: 1.0
|
||||
max_new_tokens: 150
|
||||
co2_eq_emissions:
|
||||
emissions: 86000
|
||||
source: CodeCarbon
|
||||
training_type: pre-training
|
||||
geographical_location: Germany
|
||||
hardware_used: NVIDIA A100-SXM4-80GB
|
||||
model-index:
|
||||
- name: Tucano2-qwen-3.7B-Base
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: ARC Challenge
|
||||
type: Polygl0t/ARC-poly
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 57.78
|
||||
name: Acc-norm
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: arc_challenge_poly_pt
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag
|
||||
type: Polygl0t/HellaSwag-poly
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 65.32
|
||||
name: Acc-norm
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: hellaswag_poly_pt
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Calame
|
||||
type: Polygl0t/CALAME-PT
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 61.08
|
||||
name: Acc
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: calame_pt
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Lambada
|
||||
type: Polygl0t/LAMBADA-poly
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 62.53
|
||||
name: Acc
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: lambada_pt
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Global PIQA
|
||||
type: mrlbenchmarks/global-piqa-nonparallel
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 83
|
||||
name: Acc-norm
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: global_piqa_completions_por_latn_braz
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU
|
||||
type: Polygl0t/MMLU-poly
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 65.4
|
||||
name: Acc
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: mmlu_poly_pt
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: BELEBELE
|
||||
type: facebook/belebele
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 83.67
|
||||
name: Acc-norm
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: belebele_por_Latn
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: BLUEX
|
||||
type: eduagarcia-temp/BLUEX_without_images
|
||||
split: train
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 66.2
|
||||
name: Acc
|
||||
source:
|
||||
url: https://github.com/eduagarcia/lm-evaluation-harness-pt
|
||||
name: bluex
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: ENEM Challenge
|
||||
type: eduagarcia/enem_challenge
|
||||
split: train
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 77.54
|
||||
name: Acc
|
||||
source:
|
||||
url: https://github.com/eduagarcia/lm-evaluation-harness-pt
|
||||
name: enem_challenge
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: OAB Exams
|
||||
type: eduagarcia/oab_exams
|
||||
split: train
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 58.45
|
||||
name: Acc
|
||||
source:
|
||||
url: https://github.com/eduagarcia/lm-evaluation-harness-pt
|
||||
name: oab_exams
|
||||
base_model: Qwen/Qwen3-4B-Base
|
||||
---
|
||||
|
||||
# Tucano2-qwen-3.7B-Base
|
||||
|
||||
<img src="./logo.png" alt="An illustration of a Tucano bird showing vibrant colors like yellow, orange, blue, green, and black." height="200">
|
||||
|
||||
## Model Summary
|
||||
|
||||
**[Tucano2-qwen-3.7B-Base](https://huggingface.co/Polygl0t/Tucano2-qwen-3.7B-Base)** is a decoder-only transformer continually pretrained from [Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base). Tucano2 is part of the [Polygl0t](https://huggingface.co/Polygl0t) initiative, which aims to advance language models for low-resource languages.
|
||||
|
||||
Tucano2-qwen-3.7B-Base shares the same tokenizer as **[Tucano2-0.6B-Base](https://huggingface.co/Polygl0t/Tucano2-0.6B-Base)**. Token embedding transplantation via _Orthogonal Matching Pursuit_ was used to adapt Qwen3-4B-Base to be more sensitive to the lexical, morphological, and orthographic properties of Portuguese.
|
||||
|
||||
The model was continually pretrained on approximately 50 billion tokens and achieves state-of-the-art performance across several benchmarks designed to evaluate Portuguese language models. **All data, source code, and recipes used to develop the Tucano2 series are open and fully reproducible.**
|
||||
|
||||
## Details
|
||||
|
||||
- **Architecture:** a Transformer-based model ([`qwen3`](https://huggingface.co/docs/transformers/main/en/model_doc/qwen3))
|
||||
- **Size:** 3,759,341,056 parameters
|
||||
- **Context length:** 4,096 tokens
|
||||
- **Dataset(s):**
|
||||
- [Polygl0t/gigaverbo-v2](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2)
|
||||
- [Polygl0t/gigaverbo-v2-synth](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2-synth)
|
||||
- **Language(s):** Portuguese
|
||||
- **Batch size:** 1,048,576 tokens
|
||||
- **Number of steps:** 50,000
|
||||
- **GPU:** 8 NVIDIA A100-SXM4-80GB
|
||||
- **Training time**: ~ 303 hours
|
||||
- **Emissions:** 466 KgCO2 (Germany)
|
||||
- **Total energy consumption:** 1223 kWh
|
||||
|
||||
This repository has the [source code](https://github.com/Polygl0t/llm-foundry) used to train this model. The full configuration used for training is available in the following config file:
|
||||
|
||||
- Single stage (linear warmup with cosine decay): [training_config.yaml](training_config.yaml)
|
||||
|
||||
### Checkpoints
|
||||
|
||||
Checkpoints were saved every 2,500 steps, which equates to approximately 2.5 billion tokens. The main branch of this repository contains the final checkpoint saved at step 50000. All other checkpoints are available as separate branches. To load a specific checkpoint, you can use the following code snippet:
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_id = "Polygl0t/Tucano2-qwen-3.7B-Base"
|
||||
revision = "step-2500" # Change this to the desired checkpoint branch
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, revision=revision)
|
||||
```
|
||||
|
||||
Or, you can access all the revisions for the models via the following code snippet:
|
||||
|
||||
```python
|
||||
from huggingface_hub import list_repo_refs
|
||||
out = list_repo_refs("Polygl0t/Tucano2-qwen-3.7B-Base")
|
||||
branches = [b.name for b in out.branches]
|
||||
print(branches)
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary><b>Learning Curves</b></summary>
|
||||
|
||||
|
||||
|
||||
This plot illustrates the evolution of model performance (measured by loss) as a function of training time, measured in tokens seen during training
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><b>Gradient Norms (L2)</b></summary>
|
||||
|
||||
|
||||
|
||||
This plot illustrates the evolution of gradient norms as a function of training time, measured in tokens seen during training.
|
||||
|
||||
</details>
|
||||
|
||||
## Intended Uses
|
||||
|
||||
The primary intended use of Tucano2-qwen-3.7B-Base is to serve as a foundation for research and development involving Portuguese language modeling. Checkpoints saved during training are designed to provide a controlled setting for performing comparative experiments, specifically regarding the effects of continual pretraining on the performance of currently available benchmarks. You may also fine-tune and adapt Tucano2-qwen-3.7B-Base for deployment if your use follows the Apache 2.0 license. If you decide to use Tucano2-qwen-3.7B-Base as a basis for your fine-tuned model, please conduct your own risk and bias assessment.
|
||||
|
||||
## Out-of-scope Use
|
||||
|
||||
- Tucano2-qwen-3.7B-Base is **not intended for deployment**. It is not an out-of-the-box product and should not be used for human-facing interactions.
|
||||
- Tucano2-qwen-3.7B-Base is for **the Portuguese language only** and is unsuitable for text generation tasks in other languages.
|
||||
- Tucano2-qwen-3.7B-Base has **not been fine-tuned** for downstream tasks.
|
||||
|
||||
## Basic usage
|
||||
|
||||
```python
|
||||
from transformers import GenerationConfig, TextGenerationPipeline, AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
# Specify the model and tokenizer
|
||||
model_id = "Polygl0t/Tucano2-qwen-3.7B-Base"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||||
|
||||
# Specify the generation parameters as you like
|
||||
generation_config = GenerationConfig(
|
||||
**{
|
||||
"do_sample": True,
|
||||
"max_new_tokens": 150,
|
||||
"renormalize_logits": True,
|
||||
"repetition_penalty": 1.2,
|
||||
"temperature": 0.1,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"use_cache": True,
|
||||
}
|
||||
)
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
generator = TextGenerationPipeline(model=model, task="text-generation", tokenizer=tokenizer, device=device)
|
||||
|
||||
# Generate text
|
||||
prompt = "# A floresta da Amazônia: um lugar de Magia\n\n"
|
||||
completion = generator(prompt, generation_config=generation_config)
|
||||
print(completion[0]['generated_text'])
|
||||
```
|
||||
|
||||
## Limitations
|
||||
|
||||
As almost all other language models trained on large text datasets scraped from the web, the Tucano2-qwen-3.7B-Base shows behavior that does not make it an out-of-the-box solution to many real-world applications, especially those requiring factual, reliable, and nontoxic text generation. Tucano2-qwen-3.7B-Base is subject to the following:
|
||||
|
||||
- **Hallucinations:** Tucano2-qwen-3.7B-Base can produce content that can be mistaken as facts, but is misleading or entirely false, i.e., hallucinations.
|
||||
|
||||
- **Biases and Toxicity:** Tucano2-qwen-3.7B-Base inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.
|
||||
|
||||
- **Language Limitations:** Tucano2-qwen-3.7B-Base is primarily designed to interact with Portuguese. Other languages might challenge its comprehension, leading to potential misinterpretations or errors in response.
|
||||
|
||||
- **Repetition and Verbosity:** Tucano2-qwen-3.7B-Base may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.
|
||||
|
||||
Hence, even though Tucano2-qwen-3.7B-Base is released under a permissive license, we urge users to perform their own risk analysis before using it for real-world applications.
|
||||
|
||||
## Evaluations
|
||||
|
||||
The table below compares the Tucano2 series against other base models of similar size. We divide our evaluations into two sets:
|
||||
|
||||
- **Easy Set**: CALAME, GlobalPIQA, LAMBADA, ARC-Challenge, HellaSwag
|
||||
- **Hard Set**: ENEM, BLUEX, OAB Exams, BELEBELE, MMLU
|
||||
|
||||
The NPM (Normalized Performance Metric) provides a balanced view of model performance across tasks, accounting for each task's inherent difficulty by normalizing its evaluation score relative to its random baseline.
|
||||
|
||||
| | Total Avg. | Easy Set (NPM) | Hard Set (NPM) |
|
||||
| -------------------------- | ---------- | -------------- | -------------- |
|
||||
| **Tucano2-qwen-3.7B-Base** | 59.21 | 57.41 | 61 |
|
||||
| Qwen2.5-7B | 57.97 | 54.12 | 61.83 |
|
||||
| Qwen3-4B-Base | 57.86 | 52.52 | 63.2 |
|
||||
| SmolLM3-3B-Base | 50.25 | 54.06 | 46.44 |
|
||||
| Qwen2.5-3B | 50.16 | 47.69 | 52.62 |
|
||||
| **Tucano2-qwen-1.5B-Base** | 47.9 | 47.97 | 47.82 |
|
||||
| Curio-edu-7b | 45.66 | 57.46 | 33.87 |
|
||||
| Qwen3-1.7B-Base | 44.48 | 40.94 | 48.03 |
|
||||
| Curio-7b | 42.79 | 58.97 | 26.6 |
|
||||
| Llama-3.2-3B | 40.5 | 43.79 | 37.21 |
|
||||
| granite-3.3-2b-base | 39.97 | 45.31 | 34.63 |
|
||||
| **Tucano2-qwen-0.5B-Base** | 35.36 | 39.93 | 30.79 |
|
||||
| Qwen3-0.6B-Base | 29.4 | 26.41 | 32.38 |
|
||||
| Llama-2-7b-hf | 29.36 | 42.69 | 16.03 |
|
||||
| **Tucano2-0.6B-Base** | 20.64 | 40.28 | 0.99 |
|
||||
| Qwen2.5-0.5B | 19.89 | 18.7 | 21.09 |
|
||||
| Curio-1.1b | 19.23 | 39.16 | -0.69 |
|
||||
| Tucano-2b4 | 17.88 | 33.55 | 2.2 |
|
||||
| Curio-edu-1b1 | 17.72 | 34.77 | 0.67 |
|
||||
| Llama-3.2-1B | 16.57 | 28.32 | 4.83 |
|
||||
| Tucano-1b1 | 15.44 | 29.12 | 1.76 |
|
||||
| Tucano-630m | 14.9 | 26.99 | 2.8 |
|
||||
| Carvalho_pt-gl-1.3B | 12.54 | 26.75 | -1.66 |
|
||||
| TeenyTinyLlama-460m | 11.18 | 19.65 | 2.72 |
|
||||
| Tucano-160m | 8.78 | 19.12 | -1.56 |
|
||||
| TeenyTinyLlama-160m | 7.72 | 15.75 | -0.31 |
|
||||
| GlorIA-1.3B | 5.93 | 27.27 | -15.42 |
|
||||
|
||||
<details>
|
||||
<summary><b>Evaluation Suite</b></summary>
|
||||
|
||||
| **Benchmark** | **n-shot** | **Type** | **Baseline** | **Metric** |
|
||||
| --------------- | ---------- | ------------------ | ------------ | ---------- |
|
||||
| **Easy Set** | | | | |
|
||||
| CALAME | 5-shot | Completion | 0 | `acc` |
|
||||
| GlobalPIQA | 5-shot | Completion | 50 | `acc_norm` |
|
||||
| LAMBADA | 5-shot | Completion | 0 | `acc` |
|
||||
| ARC-Challenge | 5-shot | MC-Q&A | 25 | `acc_norm` |
|
||||
| HellaSwag | 5-shot | Completion | 25 | `acc_norm` |
|
||||
| **Hard Set** | | | | |
|
||||
| ENEM | 3-shot | MC-Q&A | 20 | `acc` |
|
||||
| BLUEX | 3-shot | MC-Q&A | 22.5 | `acc` |
|
||||
| OAB Exams | 3-shot | MC-Q&A | 25 | `acc` |
|
||||
| BELEBELE | 5-shot | MC-Q&A | 25 | `acc_norm` |
|
||||
| MMLU | 5-shot | MC-Q&A | 25 | `acc` |
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><b>Individual Benchmarks</b></summary>
|
||||
|
||||
| | BLUEX | ENEM | OAB | ARC Challenge | BELEBELE | CALAME | Global PIQA | HellaSwag | LAMBADA | MMLU |
|
||||
| -------------------------- | ----- | ----- | ----- | ------------- | -------- | ------ | ----------- | --------- | ------- | ----- |
|
||||
| **Tucano2-qwen-3.7B-Base** | 66.2 | 77.54 | 58.45 | 57.78 | 83.67 | 61.08 | 83 | 65.32 | 62.53 | 65.4 |
|
||||
| Qwen2.5-7B | 65.92 | 75.02 | 55.03 | 54.19 | 89.67 | 58.96 | 78 | 67.92 | 59.52 | 68.55 |
|
||||
| Qwen3-4B-Base | 69.96 | 77.61 | 55.58 | 54.53 | 87.89 | 57.95 | 77 | 63.19 | 60.37 | 68.59 |
|
||||
| SmolLM3-3B-Base | 54.52 | 61.37 | 45.51 | 51.37 | 77.67 | 59.15 | 81 | 65.57 | 59.89 | 56.19 |
|
||||
| Qwen2.5-3B | 58.28 | 67.32 | 50.34 | 45.21 | 83.22 | 58.38 | 75 | 59.44 | 57.17 | 59.79 |
|
||||
| **Tucano2-qwen-1.5B-Base** | 55.91 | 68.72 | 48.29 | 48.21 | 74 | 59.06 | 77 | 56.25 | 54.2 | 54.04 |
|
||||
| Curio-edu-7b | 47.15 | 58.64 | 43.78 | 50.94 | 53 | 60.79 | 86 | 66.48 | 64.62 | 45.14 |
|
||||
| Qwen3-1.7B-Base | 57.16 | 65.22 | 45.79 | 47.18 | 77.89 | 53.56 | 67 | 52.55 | 50.81 | 55.49 |
|
||||
| Curio-7b | 43.39 | 50.59 | 39.68 | 48.03 | 45.33 | 63.44 | 89 | 67.58 | 65.94 | 40.83 |
|
||||
| Llama-3.2-3B | 50.35 | 53.04 | 39.45 | 41.11 | 68.89 | 54.48 | 69 | 59.14 | 59.48 | 48.28 |
|
||||
| granite-3.3-2b-base | 45.34 | 54.02 | 39.54 | 41.37 | 65.67 | 58.77 | 70 | 60.81 | 58.22 | 45.63 |
|
||||
| **Tucano2-qwen-0.5B-Base** | 46.87 | 55.14 | 40.36 | 37.44 | 53.89 | 58.67 | 74 | 48.43 | 45.14 | 39.68 |
|
||||
| Qwen3-0.6B-Base | 42.98 | 49.48 | 40.46 | 36.92 | 65 | 45.95 | 54 | 40.33 | 41.78 | 43.54 |
|
||||
| Llama-2-7b-hf | 31.29 | 31.77 | 35.49 | 42.14 | 41.44 | 54.53 | 67 | 56.76 | 59.73 | 38.64 |
|
||||
| **Tucano2-0.6B-Base** | 21.14 | 23.58 | 23.28 | 37.01 | 26.22 | 57.61 | 79 | 47.74 | 39.45 | 27.18 |
|
||||
| Qwen2.5-0.5B | 32.55 | 38.91 | 35.9 | 28.46 | 49.56 | 44.89 | 44 | 37.7 | 39.08 | 41.17 |
|
||||
| Curio-1.1b | 21.56 | 21.06 | 23.1 | 30.43 | 22.89 | 59.25 | 75 | 49.45 | 46.69 | 26.35 |
|
||||
| Tucano-2b4 | 25.45 | 21.62 | 26.74 | 30.43 | 25.89 | 50.34 | 73 | 48.85 | 32.39 | 26.24 |
|
||||
| Curio-edu-1b1 | 23.5 | 19.87 | 25.01 | 32.22 | 26.22 | 54.91 | 69 | 46.3 | 42.93 | 25.43 |
|
||||
| Llama-3.2-1B | 24.06 | 23.93 | 26.06 | 31.71 | 33.33 | 50 | 55 | 45.27 | 45.6 | 28.51 |
|
||||
| Tucano-1b1 | 25.45 | 21.55 | 26.38 | 30.09 | 25.67 | 48.94 | 68 | 44.1 | 28.43 | 25.26 |
|
||||
| Tucano-630m | 26.7 | 21.69 | 26.92 | 28.72 | 27.33 | 47.3 | 68 | 40.37 | 26.2 | 25.6 |
|
||||
| Carvalho_pt-gl-1.3B | 19.33 | 18.12 | 22.32 | 27.01 | 26.44 | 53.42 | 63 | 38.53 | 33.59 | 24.82 |
|
||||
| TeenyTinyLlama-460m | 25.87 | 20.15 | 27.02 | 27.35 | 28.11 | 42.49 | 59 | 34.81 | 21.56 | 26.65 |
|
||||
| Tucano-160m | 24.76 | 20.57 | 17.22 | 25.56 | 23.44 | 43.59 | 59 | 33.73 | 21.64 | 25.77 |
|
||||
| TeenyTinyLlama-160m | 22.53 | 18.89 | 22.32 | 24.02 | 26.78 | 39.79 | 58 | 29.89 | 17.74 | 25.74 |
|
||||
| GlorIA-1.3B | 4.31 | 2.52 | 4.69 | 26.41 | 22.78 | 54.67 | 64 | 36.35 | 36.68 | 23.69 |
|
||||
|
||||
</details>
|
||||
|
||||
## Performance and Compute
|
||||
|
||||
Below, we display the performance of Tucano2-qwen-3.7B-Base across all benchmarks in our evaluation suite. Tucano2-qwen-3.7B-Base is compared with Qwen3-4B-Base, the base model from which they were continually pretrained. The percentage variation in performance is displayed in terms of the difference in evaluation scores between the Base and the Continually Pretrained model.
|
||||
|
||||
All individual benchmark scores and their evolution across training time can be found in the [.plots](https://huggingface.co/Polygl0t/Tucano2-qwen-3.7B-Base/tree/main/.plots/) folder.
|
||||
|
||||
**Before and After Continual Pretraining**
|
||||
|
||||
|
||||
|
||||
This plot compares the compute requirements (measured as C = 6 \* N \* D, where N is the number of parameters and D is the number of tokens processed) against the performance of each model (measured by the NPM score).
|
||||
|
||||
|
||||
|
||||
<details>
|
||||
<summary><b>Performance and Compute Details</b></summary>
|
||||
|
||||
| | Parameters (B) | Pretraining Tokens (B) | Continual Pretraining Tokens (B) | Total Tokens (B) | Pretraining Compute (FLOPs) | Continual Pretraining Compute (FLOPs) | Total Compute (FLOPs) | NPM Score |
|
||||
|----------------------------|----------------|------------------------|----------------------------------|------------------|-----------------------------|---------------------------------------|-----------------------|-----------|
|
||||
| **Tucano2-qwen-3.7B-Base** | 3.7 | 36000 | 50 | 36050 | 8.64e+23 | 1.11e+21 | 8.65e+23 | 59.2 |
|
||||
| Qwen2.5-7B | 7 | 18000 | - | 18000 | 7.56e+23 | - | 7.56e+23 | 57.97 |
|
||||
| Qwen3-4B-Base | 4 | 36000 | - | 36000 | 8.64e+23 | - | 8.64e+23 | 57.86 |
|
||||
| SmolLM3-3B-Base | 3 | 11200 | - | 11200 | 2.02e+23 | - | 2.02e+23 | 50.25 |
|
||||
| Qwen2.5-3B | 3 | 18000 | - | 18000 | 3.24e+23 | - | 3.24e+23 | 50.15 |
|
||||
| **Tucano2-qwen-1.5B-Base** | 1.5 | 36000 | 100 | 36100 | 3.67e+23 | 9e+20 | 3.68e+23 | 47.89 |
|
||||
| Curio-edu-7b | 7 | 2000 | 20 | 2020 | 8.4e+22 | 8.4e+20 | 8.48e+22 | 45.66 |
|
||||
| Qwen3-1.7B-Base | 1.7 | 36000 | - | 36000 | 3.67e+23 | - | 3.67e+23 | 44.48 |
|
||||
| Curio-7b | 7 | 2000 | 150 | 2150 | 8.4e+22 | 6.3e+21 | 9.03e+22 | 42.78 |
|
||||
| Llama-3.2-3B | 3 | 9000 | - | 9000 | 1.62e+23 | - | 1.62e+23 | 40.5 |
|
||||
| granite-3.3-2b-base | 2 | 12000 | - | 12000 | 1.44e+23 | - | 1.44e+23 | 39.96 |
|
||||
| **Tucano2-qwen-0.5B-Base** | 0.5 | 36000 | 50 | 36050 | 1.3e+23 | 1.5e+20 | 1.3e+23 | 35.35 |
|
||||
| Qwen3-0.6B-Base | 0.6 | 36000 | - | 36000 | 1.3e+23 | - | 1.3e+23 | 29.39 |
|
||||
| Llama-2-7b-hf | 7 | 2000 | - | 2000 | 8.4e+22 | - | 8.4e+22 | 29.36 |
|
||||
| **Tucano2-0.6B-Base** | 0.6 | 408 | - | 408 | 1.47e+21 | - | 1.47e+21 | 20.63 |
|
||||
| Qwen2.5-0.5B | 0.5 | 18000 | - | 18000 | 5.4e+22 | - | 5.4e+22 | 19.89 |
|
||||
| Curio-1.1b | 1.1 | 1000 | 150 | 1150 | 6.6e+21 | 9.9e+20 | 7.59e+21 | 19.23 |
|
||||
| Tucano-2b4 | 2.4 | 515 | - | 515 | 7.42e+21 | - | 7.42e+21 | 17.87 |
|
||||
| Curio-edu-1b1 | 1.1 | 1000 | 20 | 1020 | 6.6e+21 | 1.32e+20 | 6.73e+21 | 17.72 |
|
||||
| Llama-3.2-1B | 1 | 9000 | - | 9000 | 5.4e+22 | - | 5.4e+22 | 16.57 |
|
||||
| Tucano-1b1 | 1.1 | 250 | - | 250 | 1.65e+21 | - | 1.65e+21 | 15.44 |
|
||||
| Tucano-630m | 0.63 | 211 | - | 211 | 7.98e+20 | - | 7.98e+20 | 14.89 |
|
||||
| Carvalho_pt-gl-1.3B | 1.3 | 26 | 5 | 31 | 2.03e+20 | 3.9e+19 | 2.42e+20 | 12.54 |
|
||||
| TeenyTinyLlama-460m | 0.46 | 6.2 | - | 6.2 | 1.71e+19 | - | 1.71e+19 | 11.18 |
|
||||
| Tucano-160m | 0.16 | 169 | - | 169 | 1.62e+20 | - | 1.62e+20 | 8.78 |
|
||||
| TeenyTinyLlama-160m | 0.16 | 6.2 | - | 6.2 | 5.95e+18 | - | 5.95e+18 | 7.71 |
|
||||
| GlorIA-1.3B | 1.3 | 35 | - | 35 | 2.73e+20 | - | 2.73e+20 | 5.92 |
|
||||
|
||||
</details>
|
||||
|
||||
## Cite as 🤗
|
||||
|
||||
```latex
|
||||
@misc{correa2026tucano2cool,
|
||||
title={{Tucano 2 Cool: Better Open Source LLMs for Portuguese}},
|
||||
author={Nicholas Kluge Corr{\^e}a and Aniket Sen and Shiza Fatimah and Sophia Falk and Lennard Landgraf and Julia Kastner and Lucie Flek},
|
||||
year={2026},
|
||||
eprint={2603.03543},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2603.03543},
|
||||
}
|
||||
```
|
||||
|
||||
## Aknowlegments
|
||||
|
||||
Polyglot is a project funded by the Federal Ministry of Education and Research (BMBF) and the Ministry of Culture and Science of the State of North Rhine-Westphalia (MWK) as part of TRA Sustainable Futures (University of Bonn) and the Excellence Strategy of the federal and state governments.
|
||||
|
||||
We also gratefully acknowledge the granted access to the [Marvin cluster](https://www.hpc.uni-bonn.de/en/systems/marvin) hosted by [University of Bonn](https://www.uni-bonn.de/en) along with the support provided by its High Performance Computing & Analytics Lab.
|
||||
|
||||
## License
|
||||
|
||||
Tucano2-qwen-3.7B-Base is licensed under the Apache License, Version 2.0. For more details, see the [LICENSE](LICENSE) file.
|
||||
70
config.json
Normal file
70
config.json
Normal file
@@ -0,0 +1,70 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 4096,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 49109,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.53.2",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
23
emissions.csv
Normal file
23
emissions.csv
Normal file
@@ -0,0 +1,23 @@
|
||||
timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
||||
2026-01-15T18:36:21,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,2468.154875099659,0.5195039106304847,0.0002104827034444,45.027290925,365.33355990502815,70.0,0.0298295135649475,1.287542577533486,0.0463341974708924,1.363706288569326,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-16T09:06:58,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,54704.4767507948,11.595711822278624,0.0002119700710254,45.02626823769232,364.31659250401066,70.0,0.6612322660173141,28.75075110169371,1.0269504091064288,30.438933776817496,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-17T00:14:10,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,109136.3574270364,23.13841512055636,0.0002120138115845,45.033781860000005,366.0656712431605,70.0,1.319176990428561,57.37075434434462,2.048787973683132,60.7387193084561,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-17T15:21:21,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,163567.73299597765,34.67404203491055,0.000211985832412,45.02352758400001,365.6402060708027,70.0,1.9771126242558168,85.97220533993158,3.0706112520106603,91.01992921619778,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-18T06:28:30,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,217997.1265374664,46.20552631578055,0.0002119547493569,45.02980962,368.02914726819273,70.0,2.635007360849327,114.56288697912528,4.092370303104284,121.29026464307798,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-18T21:35:36,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,272423.1234841924,57.7453517586373,0.0002119693476093,45.023594388750006,366.0163927822049,70.0,3.292879428269992,143.1755286803314,5.114087648420479,151.58249575702138,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-19T12:42:46,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,326852.9779706467,69.2843478887053,0.0002119740450855,45.019291527,365.1986956207545,70.0,3.9508097393555017,171.78584064300725,6.135899528926718,181.8725499112884,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-20T03:49:46,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,381273.3088904135,80.82208866270898,0.0002119794036931,45.02813139346154,366.5763535291482,70.0,4.608630381110712,200.3931514191152,7.157526935066201,212.1593087352907,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-20T18:56:48,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,435694.7253034543,92.36224746237993,0.0002119884453456,45.02399466681818,365.5611996992909,70.0,5.266440596559091,229.00681658280672,8.179157736976183,242.45241491634053,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-21T10:03:57,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,490123.6352933403,103.90027516583852,0.0002119878897569,45.0380538,362.73561379820666,70.0,5.924347015764262,257.6146445718286,9.200935347279996,272.73992693486946,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-22T01:10:57,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,544543.8373416401,115.4391691490337,0.000211992426014,45.025143291,364.764783523692,70.0,6.582147076467519,286.2250175984421,10.222548277012152,303.0297129519194,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-22T16:22:42,Polyglot,a98dcd1d-81e8-4c52-b9ba-98152119eb2c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,599248.5571675301,127.00066561859128,0.0002119332021738,45.022997385,365.56758633067534,70.0,7.243476923541371,314.88571718170573,11.24963676124982,333.37883086649504,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-23T12:45:51,Polyglot,2484ccec-2100-4c4c-b6e6-435ed2c585ba,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,54613.77945225686,11.550126398496984,0.0002114874032586,45.03137619681819,364.7858089641286,70.0,0.6601663593915156,28.63382480287487,1.0252801292337537,30.31927129150016,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-24T03:53:26,Polyglot,2484ccec-2100-4c4c-b6e6-435ed2c585ba,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,109069.18703039364,23.095515196498937,0.0002117510529354,45.02650497576924,365.02014175589295,70.0,1.3184111013187851,57.260129715011885,2.0475654876437246,60.62610630397411,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-24T19:00:52,Polyglot,2484ccec-2100-4c4c-b6e6-435ed2c585ba,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,163514.35428753495,34.6420400613965,0.0002118593209283,45.0275499225,363.8928029652876,70.0,1.97649903696516,85.88980653234592,3.069617941376579,90.93592351068774,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-25T10:08:17,Polyglot,2484ccec-2100-4c4c-b6e6-435ed2c585ba,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,217959.6767143328,46.19001499252549,0.0002119200013911,45.0285341535,364.1332683805725,70.0,2.634615922478797,114.52321929127991,4.091711951290329,121.2495471650492,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-26T12:55:19,Polyglot,2056727d-5a23-4012-8dc1-d9ed973eafe3,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,54645.26329020783,11.564505259260228,0.0002116286858724,45.02202440625,366.6509312989584,70.0,0.6605413594542934,28.67061471564012,1.0258599618138646,30.35701603690833,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-28T09:16:38,Polyglot,44d02a14-b9c1-4b54-96eb-262e07ddb7aa,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,54667.189970373,12.630934188028013,0.0002310514624013,225.0,364.96770478698727,70.0,3.4129260209240755,28.681692707280227,1.0617907429283409,33.156409471132726,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-01-29T00:24:39,Polyglot,44d02a14-b9c1-4b54-96eb-262e07ddb7aa,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,109148.035300284,25.27580870613449,0.0002315736479964,225.0,366.0242192060592,70.0,6.8141945241443445,57.41526349217393,2.119954521113271,66.3494125374314,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-02-02T11:01:39,Polyglot,a7a5d34d-5890-4e6c-8818-fee6be214e64,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,54529.717731854005,11.516054625936697,0.0002111885977948,45.00559872,370.8932572897432,70.0,0.6591468596468995,28.54703232066313,1.023653149225791,30.229832329535885,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-02-03T04:10:53,Polyglot,58b3e182-5987-4f0f-90c8-34d6a56e3290,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,54836.62605299696,11.529045078499776,0.0002102435162104,45.031022775,364.51114155448056,70.0,0.6628703193037179,28.57158590252822,1.0294762588080826,30.26393248063992,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
2026-02-03T04:11:15,Polyglot,58b3e182-5987-4f0f-90c8-34d6a56e3290,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,54858.70311053004,11.533777165940318,0.00021024516643606961,45.000000405,475.9117209547019,70.0,0.6633147701490933,28.58287248572414,1.0301670319345049,30.276354287807635,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.6,256,AMD EPYC 7713 64-Core Processor,4,4 x NVIDIA A100-SXM4-80GB,7.0932,50.7263,1950,machine,N,1.0
|
||||
|
190
evals.yaml
Normal file
190
evals.yaml
Normal file
@@ -0,0 +1,190 @@
|
||||
evaluations:
|
||||
arc_challenge_poly_pt_acc: 0.5230769230769231
|
||||
arc_challenge_poly_pt_acc_norm: 0.5777777777777777
|
||||
arc_challenge_poly_pt_acc_norm_stderr: 0.014445870094078068
|
||||
arc_challenge_poly_pt_acc_stderr: 0.014608300475750825
|
||||
arc_challenge_poly_pt_alias: arc_challenge_poly_pt
|
||||
assin2_rte_acc,all: 0.9252450980392157
|
||||
assin2_rte_acc_stderr,all: 0.0037560275279046665
|
||||
assin2_rte_alias: assin2_rte
|
||||
assin2_rte_f1_macro,all: 0.9251590635527494
|
||||
assin2_rte_f1_macro_stderr,all: 0.0037610728425282497
|
||||
assin2_sts_alias: assin2_sts
|
||||
assin2_sts_mse,all: 0.5572916666666665
|
||||
assin2_sts_mse_stderr,all: N/A
|
||||
assin2_sts_pearson,all: 0.7701197353926412
|
||||
assin2_sts_pearson_stderr,all: 0.006649667590414615
|
||||
assin_entailment_acc: 0.704
|
||||
assin_entailment_acc_stderr: 0.00721865827261647
|
||||
assin_entailment_alias: assin_entailment
|
||||
assin_paraphrase_acc: 0.694
|
||||
assin_paraphrase_acc_stderr: 0.007287268079947193
|
||||
assin_paraphrase_alias: assin_paraphrase
|
||||
belebele_por_Latn_acc: 0.8366666666666667
|
||||
belebele_por_Latn_acc_norm: 0.8366666666666667
|
||||
belebele_por_Latn_acc_norm_stderr: 0.012329168844652528
|
||||
belebele_por_Latn_acc_stderr: 0.012329168844652528
|
||||
belebele_por_Latn_alias: belebele_por_Latn
|
||||
bluex_acc,all: 0.6620305980528511
|
||||
bluex_acc,exam_id__UNICAMP_2018: 0.6481481481481481
|
||||
bluex_acc,exam_id__UNICAMP_2019: 0.64
|
||||
bluex_acc,exam_id__UNICAMP_2020: 0.6909090909090909
|
||||
bluex_acc,exam_id__UNICAMP_2021_1: 0.6521739130434783
|
||||
bluex_acc,exam_id__UNICAMP_2021_2: 0.5882352941176471
|
||||
bluex_acc,exam_id__UNICAMP_2022: 0.6666666666666666
|
||||
bluex_acc,exam_id__UNICAMP_2023: 0.7209302325581395
|
||||
bluex_acc,exam_id__UNICAMP_2024: 0.6444444444444445
|
||||
bluex_acc,exam_id__USP_2018: 0.5925925925925926
|
||||
bluex_acc,exam_id__USP_2019: 0.7
|
||||
bluex_acc,exam_id__USP_2020: 0.6607142857142857
|
||||
bluex_acc,exam_id__USP_2021: 0.75
|
||||
bluex_acc,exam_id__USP_2022: 0.5918367346938775
|
||||
bluex_acc,exam_id__USP_2023: 0.7045454545454546
|
||||
bluex_acc,exam_id__USP_2024: 0.7073170731707317
|
||||
bluex_acc_stderr,all: 0.010157757528559894
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2018: 0.037594875406546435
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2019: 0.03953375278949041
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2020: 0.03605420458368598
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2021_1: 0.0405315180666698
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2021_2: 0.039752636457935614
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2022: 0.04360776726045774
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2023: 0.039432470230869696
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2024: 0.041213076472343936
|
||||
bluex_acc_stderr,exam_id__USP_2018: 0.038650432775192395
|
||||
bluex_acc_stderr,exam_id__USP_2019: 0.04175277819931915
|
||||
bluex_acc_stderr,exam_id__USP_2020: 0.03644397183647981
|
||||
bluex_acc_stderr,exam_id__USP_2021: 0.034773619645811646
|
||||
bluex_acc_stderr,exam_id__USP_2022: 0.040532053004604704
|
||||
bluex_acc_stderr,exam_id__USP_2023: 0.039742872820681924
|
||||
bluex_acc_stderr,exam_id__USP_2024: 0.040951553558739306
|
||||
bluex_alias: bluex
|
||||
calame_pt_acc: 0.6107899807321773
|
||||
calame_pt_acc_stderr: 0.0107035762556229
|
||||
calame_pt_alias: calame_pt
|
||||
calame_pt_perplexity: 5.713055201421455
|
||||
calame_pt_perplexity_stderr: 0.29495381614560345
|
||||
enem_challenge_acc,all: 0.7753673897830651
|
||||
enem_challenge_acc,exam_id__2009: 0.7478260869565218
|
||||
enem_challenge_acc,exam_id__2010: 0.811965811965812
|
||||
enem_challenge_acc,exam_id__2011: 0.8461538461538461
|
||||
enem_challenge_acc,exam_id__2012: 0.8448275862068966
|
||||
enem_challenge_acc,exam_id__2013: 0.7777777777777778
|
||||
enem_challenge_acc,exam_id__2014: 0.8073394495412844
|
||||
enem_challenge_acc,exam_id__2015: 0.8067226890756303
|
||||
enem_challenge_acc,exam_id__2016: 0.743801652892562
|
||||
enem_challenge_acc,exam_id__2016_2: 0.7154471544715447
|
||||
enem_challenge_acc,exam_id__2017: 0.75
|
||||
enem_challenge_acc,exam_id__2022: 0.6842105263157895
|
||||
enem_challenge_acc,exam_id__2023: 0.7851851851851852
|
||||
enem_challenge_acc_stderr,all: 0.006377145135723042
|
||||
enem_challenge_acc_stderr,exam_id__2009: 0.023447252641875988
|
||||
enem_challenge_acc_stderr,exam_id__2010: 0.02087704326839612
|
||||
enem_challenge_acc_stderr,exam_id__2011: 0.01921565112452091
|
||||
enem_challenge_acc_stderr,exam_id__2012: 0.01944793905815595
|
||||
enem_challenge_acc_stderr,exam_id__2013: 0.023084030560191867
|
||||
enem_challenge_acc_stderr,exam_id__2014: 0.021892563584984096
|
||||
enem_challenge_acc_stderr,exam_id__2015: 0.020893018955083217
|
||||
enem_challenge_acc_stderr,exam_id__2016: 0.022776450345788787
|
||||
enem_challenge_acc_stderr,exam_id__2016_2: 0.023503035027562222
|
||||
enem_challenge_acc_stderr,exam_id__2017: 0.023138027075607918
|
||||
enem_challenge_acc_stderr,exam_id__2022: 0.02320588990454305
|
||||
enem_challenge_acc_stderr,exam_id__2023: 0.020404682391600704
|
||||
enem_challenge_alias: enem
|
||||
faquad_nli_acc,all: 0.7876923076923077
|
||||
faquad_nli_acc_stderr,all: 0.01133278097111669
|
||||
faquad_nli_alias: faquad_nli
|
||||
faquad_nli_f1_macro,all: 0.45449901481427424
|
||||
faquad_nli_f1_macro_stderr,all: 0.008069363645658589
|
||||
global_piqa_completions_por_latn_braz_acc: 0.84
|
||||
global_piqa_completions_por_latn_braz_acc_bytes: 0.83
|
||||
global_piqa_completions_por_latn_braz_acc_bytes_stderr: 0.03775251680686369
|
||||
global_piqa_completions_por_latn_braz_acc_norm: 0.83
|
||||
global_piqa_completions_por_latn_braz_acc_norm_stderr: 0.03775251680686369
|
||||
global_piqa_completions_por_latn_braz_acc_stderr: 0.03684529491774706
|
||||
global_piqa_completions_por_latn_braz_alias: global_piqa_completions_por_latn_braz
|
||||
hatebr_offensive_acc,all: 0.665
|
||||
hatebr_offensive_acc_stderr,all: 0.00890653495166499
|
||||
hatebr_offensive_alias: hatebr_offensive_binary
|
||||
hatebr_offensive_f1_macro,all: 0.6234605955470173
|
||||
hatebr_offensive_f1_macro_stderr,all: 0.00951858317428499
|
||||
hellaswag_poly_pt_acc: 0.4838010618701918
|
||||
hellaswag_poly_pt_acc_norm: 0.6531585220500596
|
||||
hellaswag_poly_pt_acc_norm_stderr: 0.004954741713215018
|
||||
hellaswag_poly_pt_acc_stderr: 0.00520221346811777
|
||||
hellaswag_poly_pt_alias: hellaswag_poly_pt
|
||||
lambada_poly_pt_acc: 0.6252668348534834
|
||||
lambada_poly_pt_acc_stderr: 0.006743817908692071
|
||||
lambada_poly_pt_alias: lambada_poly_pt
|
||||
lambada_poly_pt_perplexity: 6.574656712295472
|
||||
lambada_poly_pt_perplexity_stderr: 0.18832300331707774
|
||||
mmlu_poly_pt_acc: 0.6540078054638246
|
||||
mmlu_poly_pt_acc_stderr: 0.004121199159002156
|
||||
mmlu_poly_pt_alias: mmlu_poly_pt
|
||||
oab_exams_acc,all: 0.584510250569476
|
||||
oab_exams_acc,exam_id__2010-01: 0.3764705882352941
|
||||
oab_exams_acc,exam_id__2010-02: 0.59
|
||||
oab_exams_acc,exam_id__2011-03: 0.5656565656565656
|
||||
oab_exams_acc,exam_id__2011-04: 0.5125
|
||||
oab_exams_acc,exam_id__2011-05: 0.6625
|
||||
oab_exams_acc,exam_id__2012-06: 0.625
|
||||
oab_exams_acc,exam_id__2012-06a: 0.7375
|
||||
oab_exams_acc,exam_id__2012-07: 0.6125
|
||||
oab_exams_acc,exam_id__2012-08: 0.55
|
||||
oab_exams_acc,exam_id__2012-09: 0.4805194805194805
|
||||
oab_exams_acc,exam_id__2013-10: 0.65
|
||||
oab_exams_acc,exam_id__2013-11: 0.625
|
||||
oab_exams_acc,exam_id__2013-12: 0.65
|
||||
oab_exams_acc,exam_id__2014-13: 0.525
|
||||
oab_exams_acc,exam_id__2014-14: 0.625
|
||||
oab_exams_acc,exam_id__2014-15: 0.6538461538461539
|
||||
oab_exams_acc,exam_id__2015-16: 0.5875
|
||||
oab_exams_acc,exam_id__2015-17: 0.5897435897435898
|
||||
oab_exams_acc,exam_id__2015-18: 0.575
|
||||
oab_exams_acc,exam_id__2016-19: 0.5897435897435898
|
||||
oab_exams_acc,exam_id__2016-20: 0.6125
|
||||
oab_exams_acc,exam_id__2016-20a: 0.55
|
||||
oab_exams_acc,exam_id__2016-21: 0.4875
|
||||
oab_exams_acc,exam_id__2017-22: 0.6375
|
||||
oab_exams_acc,exam_id__2017-23: 0.525
|
||||
oab_exams_acc,exam_id__2017-24: 0.6375
|
||||
oab_exams_acc,exam_id__2018-25: 0.5625
|
||||
oab_exams_acc_stderr,all: 0.006071412237214423
|
||||
oab_exams_acc_stderr,exam_id__2010-01: 0.030361740131894334
|
||||
oab_exams_acc_stderr,exam_id__2010-02: 0.028445183897774385
|
||||
oab_exams_acc_stderr,exam_id__2011-03: 0.02862790167127372
|
||||
oab_exams_acc_stderr,exam_id__2011-04: 0.03224493616787287
|
||||
oab_exams_acc_stderr,exam_id__2011-05: 0.030467009008680036
|
||||
oab_exams_acc_stderr,exam_id__2012-06: 0.031220571629946996
|
||||
oab_exams_acc_stderr,exam_id__2012-06a: 0.02843559794708646
|
||||
oab_exams_acc_stderr,exam_id__2012-07: 0.03139589988285276
|
||||
oab_exams_acc_stderr,exam_id__2012-08: 0.03226132851591818
|
||||
oab_exams_acc_stderr,exam_id__2012-09: 0.032830805301195386
|
||||
oab_exams_acc_stderr,exam_id__2013-10: 0.030611536360793473
|
||||
oab_exams_acc_stderr,exam_id__2013-11: 0.031310092407276585
|
||||
oab_exams_acc_stderr,exam_id__2013-12: 0.030692719997990617
|
||||
oab_exams_acc_stderr,exam_id__2014-13: 0.032358129209763435
|
||||
oab_exams_acc_stderr,exam_id__2014-14: 0.031382714558388446
|
||||
oab_exams_acc_stderr,exam_id__2014-15: 0.03109637957099322
|
||||
oab_exams_acc_stderr,exam_id__2015-16: 0.031957806650269406
|
||||
oab_exams_acc_stderr,exam_id__2015-17: 0.03208206142728883
|
||||
oab_exams_acc_stderr,exam_id__2015-18: 0.03182114971496286
|
||||
oab_exams_acc_stderr,exam_id__2016-19: 0.03228511767428725
|
||||
oab_exams_acc_stderr,exam_id__2016-20: 0.031372223696958024
|
||||
oab_exams_acc_stderr,exam_id__2016-20a: 0.0321935167686262
|
||||
oab_exams_acc_stderr,exam_id__2016-21: 0.03209267502993051
|
||||
oab_exams_acc_stderr,exam_id__2017-22: 0.03105400471909683
|
||||
oab_exams_acc_stderr,exam_id__2017-23: 0.03235792164586319
|
||||
oab_exams_acc_stderr,exam_id__2017-24: 0.031098329350728315
|
||||
oab_exams_acc_stderr,exam_id__2018-25: 0.03209246971016282
|
||||
oab_exams_alias: oab_exams
|
||||
portuguese_hate_speech_acc,all: 0.6145710928319624
|
||||
portuguese_hate_speech_acc_stderr,all: 0.011835075822813054
|
||||
portuguese_hate_speech_alias: portuguese_hate_speech_binary
|
||||
portuguese_hate_speech_f1_macro,all: 0.6103088177807561
|
||||
portuguese_hate_speech_f1_macro_stderr,all: 0.011900091760317547
|
||||
tweetsentbr_acc,all: 0.7298507462686568
|
||||
tweetsentbr_acc_stderr,all: 0.006986496038388035
|
||||
tweetsentbr_alias: tweetsentbr
|
||||
tweetsentbr_f1_macro,all: 0.7027752533485003
|
||||
tweetsentbr_f1_macro_stderr,all: 0.007392699151541939
|
||||
step: 50000
|
||||
22
evals_all_steps.csv
Normal file
22
evals_all_steps.csv
Normal file
File diff suppressed because one or more lines are too long
27
evals_for_comparison.csv
Normal file
27
evals_for_comparison.csv
Normal file
File diff suppressed because one or more lines are too long
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 49109,
|
||||
"transformers_version": "4.53.2",
|
||||
"do_sample": true,
|
||||
"max_new_tokens": 1024,
|
||||
"renormalize_logits": true,
|
||||
"repetition_penalty": 1.2,
|
||||
"temperature": 0.1,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"use_cache": false
|
||||
}
|
||||
3
logo.png
Normal file
3
logo.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1856d91c3b35390cee5122902d94044657c67df7034ca4005316275c404fc8a0
|
||||
size 197189
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:869e1d78e03c3f52e59df11c36b7409a393fb33c1a9a990d2c443b1505390122
|
||||
size 4996742472
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7de28cf45b0c898934748c85b310680f859797b417666e05dbd5b2246225d0ee
|
||||
size 2773643768
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3759341056,
|
||||
"total_size": 7770340352
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
82
ruler.yaml
Normal file
82
ruler.yaml
Normal file
@@ -0,0 +1,82 @@
|
||||
model_name: Tucano2-qwen-3.7B-Base
|
||||
results:
|
||||
niah_pt_multikey_1_1024: 0.596
|
||||
niah_pt_multikey_1_1024_stderr: 0.021966635293832883
|
||||
niah_pt_multikey_1_2048: 0.614
|
||||
niah_pt_multikey_1_2048_stderr: 0.021793529219281196
|
||||
niah_pt_multikey_1_4096: 0.436
|
||||
niah_pt_multikey_1_4096_stderr: N/A
|
||||
niah_pt_multikey_1_alias: " - niah_pt_multikey_1"
|
||||
niah_pt_multikey_2_1024: 0.67
|
||||
niah_pt_multikey_2_1024_stderr: 0.021049612166134782
|
||||
niah_pt_multikey_2_2048: 0.682
|
||||
niah_pt_multikey_2_2048_stderr: 0.020847571620814014
|
||||
niah_pt_multikey_2_4096: 0.608
|
||||
niah_pt_multikey_2_4096_stderr: N/A
|
||||
niah_pt_multikey_2_alias: " - niah_pt_multikey_2"
|
||||
niah_pt_multikey_3_1024: 0.842
|
||||
niah_pt_multikey_3_1024_stderr: 0.0163280498045799
|
||||
niah_pt_multikey_3_2048: 0.856
|
||||
niah_pt_multikey_3_2048_stderr: 0.015716934945725784
|
||||
niah_pt_multikey_3_4096: 0.786
|
||||
niah_pt_multikey_3_4096_stderr: N/A
|
||||
niah_pt_multikey_3_alias: " - niah_pt_multikey_3"
|
||||
niah_pt_multiquery_1024: 0.5815
|
||||
niah_pt_multiquery_1024_stderr: 0.015245666949052864
|
||||
niah_pt_multiquery_2048: 0.5405
|
||||
niah_pt_multiquery_2048_stderr: 0.014383437229433934
|
||||
niah_pt_multiquery_4096: 0.493
|
||||
niah_pt_multiquery_4096_stderr: N/A
|
||||
niah_pt_multiquery_alias: " - niah_pt_multiquery"
|
||||
niah_pt_multivalue_1024: 0.5685
|
||||
niah_pt_multivalue_1024_stderr: 0.015209475872383808
|
||||
niah_pt_multivalue_2048: 0.3425
|
||||
niah_pt_multivalue_2048_stderr: 0.014868747738751817
|
||||
niah_pt_multivalue_4096: 0.355
|
||||
niah_pt_multivalue_4096_stderr: N/A
|
||||
niah_pt_multivalue_alias: " - niah_pt_multivalue"
|
||||
niah_pt_single_1_1024: 0.63
|
||||
niah_pt_single_1_1024_stderr: 0.021613289165165816
|
||||
niah_pt_single_1_2048: 0.578
|
||||
niah_pt_single_1_2048_stderr: 0.022109039310618563
|
||||
niah_pt_single_1_4096: 0.462
|
||||
niah_pt_single_1_4096_stderr: N/A
|
||||
niah_pt_single_1_alias: " - niah_pt_single_1"
|
||||
niah_pt_single_2_1024: 0.538
|
||||
niah_pt_single_2_1024_stderr: 0.022318338119870523
|
||||
niah_pt_single_2_2048: 0.548
|
||||
niah_pt_single_2_2048_stderr: 0.02227969410784354
|
||||
niah_pt_single_2_4096: 0.566
|
||||
niah_pt_single_2_4096_stderr: N/A
|
||||
niah_pt_single_2_alias: " - niah_pt_single_2"
|
||||
niah_pt_single_3_1024: 0.716
|
||||
niah_pt_single_3_1024_stderr: 0.020186703693570777
|
||||
niah_pt_single_3_2048: 0.726
|
||||
niah_pt_single_3_2048_stderr: 0.019966103540279518
|
||||
niah_pt_single_3_4096: 0.702
|
||||
niah_pt_single_3_4096_stderr: N/A
|
||||
niah_pt_single_3_alias: " - niah_pt_single_3"
|
||||
ruler_pt_4096: 0.5871696969696969
|
||||
ruler_pt_4096_stderr: N/A
|
||||
ruler_pt_alias: ruler_pt
|
||||
ruler_pt_cwe_1024: 0.3028
|
||||
ruler_pt_cwe_1024_stderr: 0.0064114376754463
|
||||
ruler_pt_cwe_2048: 0.253
|
||||
ruler_pt_cwe_2048_stderr: 0.006635515060659607
|
||||
ruler_pt_cwe_4096: 0.3358
|
||||
ruler_pt_cwe_4096_stderr: N/A
|
||||
ruler_pt_cwe_alias: " - ruler_pt_cwe"
|
||||
ruler_pt_fwe_1024: 0.864
|
||||
ruler_pt_fwe_1024_stderr: 0.010004852975181538
|
||||
ruler_pt_fwe_2048: 0.8266666666666667
|
||||
ruler_pt_fwe_2048_stderr: 0.011102646519713471
|
||||
ruler_pt_fwe_4096: 0.7346666666666666
|
||||
ruler_pt_fwe_4096_stderr: N/A
|
||||
ruler_pt_fwe_alias: " - ruler_pt_fwe"
|
||||
ruler_pt_vt_1024: 0.9816
|
||||
ruler_pt_vt_1024_stderr: 0.004767424532527671
|
||||
ruler_pt_vt_2048: 0.9708
|
||||
ruler_pt_vt_2048_stderr: 0.006233171331649675
|
||||
ruler_pt_vt_4096: 0.9803999999999999
|
||||
ruler_pt_vt_4096_stderr: N/A
|
||||
ruler_pt_vt_alias: " - ruler_pt_vt"
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|unk|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
463711
tokenizer.json
Normal file
463711
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
397
tokenizer_config.json
Normal file
397
tokenizer_config.json
Normal file
@@ -0,0 +1,397 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|unk|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49109": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49110": {
|
||||
"content": "<tools>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49111": {
|
||||
"content": "</tools>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49112": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49113": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49114": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49115": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49116": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49117": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49118": {
|
||||
"content": "<answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49119": {
|
||||
"content": "</answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49120": {
|
||||
"content": "<context>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49121": {
|
||||
"content": "</context>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49122": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49123": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49124": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49125": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49126": {
|
||||
"content": "<|image|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49127": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49128": {
|
||||
"content": "<|image_placeholder|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49129": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49130": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49131": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49132": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49133": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49134": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49135": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49136": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49137": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49138": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49139": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49140": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49141": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49142": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49143": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49144": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49145": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49146": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49147": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49148": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49149": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49150": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"49151": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|im_start|>",
|
||||
"bos_token_id": 1,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"eos_token_id": 2,
|
||||
"extra_special_tokens": {},
|
||||
"legacy": false,
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<|pad|>",
|
||||
"pad_token_id": 49109,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "PreTrainedTokenizerFast",
|
||||
"truncation_side": "right",
|
||||
"unk_token": "<|unk|>",
|
||||
"unk_token_id": 0,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
3
train_logs.parquet
Normal file
3
train_logs.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b8b5e183f71ab4fafad5f542e54f1cf231935a2de4d14f1d0b67e23fd4ebc499
|
||||
size 1292663
|
||||
99
training_config.yaml
Normal file
99
training_config.yaml
Normal file
@@ -0,0 +1,99 @@
|
||||
# Directory settings
|
||||
checkpoint_dir: "/lustre/scratch/data/polyglot_datasets/portuguese/checkpoints/models/Tucano2-qwen-3.7B-Base"
|
||||
train_dataset_dir:
|
||||
# Total: ~48B
|
||||
# # Web Text (~28B, 58%)
|
||||
- /lustre/scratch/data/polyglot_datasets/portuguese/tokenized/gigaverbo_v2/4 # 28B (PT)
|
||||
- /lustre/scratch/data/polyglot_datasets/portuguese/tokenized/gigaverbo_v2/5 # 0.1B (PT)
|
||||
- /lustre/scratch/data/polyglot_datasets/portuguese/tokenized/gigaverbo_v2/5 # 0.1B (PT)
|
||||
# # Synthetic Text (~20B, 42%)
|
||||
- /lustre/scratch/data/polyglot_datasets/portuguese/tokenized/gigaverbo_v2_synth # 10B (PT)
|
||||
- /lustre/scratch/data/polyglot_datasets/portuguese/tokenized/gigaverbo_v2_synth # 10B (PT)
|
||||
val_dataset_dir: "/lustre/scratch/data/polyglot_datasets/portuguese/tokenized/validation"
|
||||
dataset_type: "parquet"
|
||||
cache_dir: "/lustre/scratch/data/polyglot_datasets/.cache"
|
||||
|
||||
# Data loading settings
|
||||
pin_memory: true
|
||||
num_workers_for_dataloader: 16
|
||||
prefetch_factor: 4
|
||||
shuffle_dataset: true
|
||||
mask_eos_token: false
|
||||
mask_pad_token: false
|
||||
|
||||
# Model architecture settings
|
||||
vocab_size: 49152
|
||||
num_hidden_layers: 36
|
||||
num_attention_heads: 32
|
||||
num_key_value_heads: 8
|
||||
head_dim: 128
|
||||
hidden_size: 2560
|
||||
intermediate_size: 9728
|
||||
max_position_embeddings: 4096
|
||||
tie_word_embeddings: true
|
||||
hidden_act: "silu"
|
||||
output_hidden_states: false
|
||||
attn_implementation: "flash_attention_2"
|
||||
use_cache: false
|
||||
no_rope_layer_interval: null
|
||||
rope_theta: 1000000.0
|
||||
rope_scale_factor: null
|
||||
rms_norm_eps: 0.000001
|
||||
|
||||
# Training settings
|
||||
total_batch_size: 1048576
|
||||
micro_batch_size: 16
|
||||
eval_micro_batch_size: 16
|
||||
num_train_epochs: 1
|
||||
warmup_steps: 100
|
||||
max_learning_rate: 0.000075
|
||||
min_learning_rate: 0.0
|
||||
muon_learning_rate: 0.001
|
||||
weight_decay: 0.1
|
||||
beta1: 0.9
|
||||
beta2: 0.95
|
||||
eps: 0.00000001
|
||||
lr_decay_type: "cosine"
|
||||
use_sqrt: true
|
||||
lr_decay_iters_coef: 1.
|
||||
seed: 42
|
||||
max_steps: 50000
|
||||
max_grad_norm: 1.0
|
||||
|
||||
# Precision, optimization, and sharding settings
|
||||
torch_compile: false
|
||||
mat_mul_precision: "highest"
|
||||
tf32: true
|
||||
bf16: true
|
||||
gradient_checkpointing: true
|
||||
use_liger_kernel: true
|
||||
fsdp_mixed_precision: true
|
||||
dp_shard: null
|
||||
full_shard: false
|
||||
cpu_offload: false
|
||||
explicit_prefetching: true
|
||||
|
||||
# Hub settings
|
||||
push_to_hub: false
|
||||
hub_token: null
|
||||
hub_model_id: null
|
||||
|
||||
# Tokenizer and Reference model
|
||||
tokenizer_name_or_path: "/lustre/scratch/data/polyglot_datasets/portuguese/checkpoints/models/Tucano2-qwen-3.7B-Base/step-0"
|
||||
chat_template_path: null
|
||||
reference_model: "/lustre/scratch/data/polyglot_datasets/portuguese/checkpoints/models/Tucano2-qwen-3.7B-Base/step-0"
|
||||
continual_pretraining: true
|
||||
|
||||
# Checkpoint settings
|
||||
resume_from_checkpoint: null
|
||||
checkpointing_steps: 2500
|
||||
begin_new_stage: false
|
||||
stage_name: "single_cosine"
|
||||
|
||||
# Miscellaneous settings
|
||||
sanity_check: false
|
||||
sanity_check_num_samples: 100000
|
||||
wandb_token: null
|
||||
wandb_id: "tucano2-qwen-3.7b"
|
||||
wandb_project: "Polyglot"
|
||||
wandb_desc: "Developing LLMs for low-resource languages"
|
||||
3
val_logs.parquet
Normal file
3
val_logs.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b3be7f2668b7854e5f47eac5ca1497515931bb63aed477d8003e99d58c110d22
|
||||
size 1948
|
||||
Reference in New Issue
Block a user