初始化项目，由ModelHub XC社区提供模型
Model: Polygl0t/Tucano2-qwen-1.5B-Instruct Source: Original Platform
This commit is contained in:
ModelHub XC
41
.gitattributes
vendored
Normal file
41
.gitattributes
vendored
Normal file
@@ -0,0 +1,41 @@
|
|||||||
|
*.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/apo_gradient_norm.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
.plots/apo_reward.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
.plots/model_comparison.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
.plots/sft_gradient_norm.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
.plots/sft_loss.png filter=lfs diff=lfs merge=lfs -text
|
||||||
3
.plots/apo_gradient_norm.png
Normal file
3
.plots/apo_gradient_norm.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e432ac2db3d283bd1d7fa03aca2af0988c7292579be48ae869db1b75f820f745
|
||||||
|
size 415968
|
||||||
3
.plots/apo_reward.png
Normal file
3
.plots/apo_reward.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c2557e0fb5921da64ad89843f846c30bb8ffcc6ada843229fa5e0217d17ee91c
|
||||||
|
size 289072
|
||||||
3
.plots/model_comparison.png
Normal file
3
.plots/model_comparison.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7e86ad27695f352e94beecf6bb3b995b195248102daa1be6e8af163b78bc7988
|
||||||
|
size 244412
|
||||||
3
.plots/sft_gradient_norm.png
Normal file
3
.plots/sft_gradient_norm.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bec707718f5045f8605e9abf8921692e1132e833ccdbebfecb9a0c9fad76ca06
|
||||||
|
size 269147
|
||||||
3
.plots/sft_loss.png
Normal file
3
.plots/sft_loss.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aad44bb4c38a9a06d3e5bf485c4620e3b53f2859c84d0b483faba879af0b8687
|
||||||
|
size 273046
|
||||||
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.
|
||||||
521
README.md
Normal file
521
README.md
Normal file
@@ -0,0 +1,521 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- pt
|
||||||
|
license: apache-2.0
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
datasets:
|
||||||
|
- Polygl0t/gigaverbo-v2-sft
|
||||||
|
- Polygl0t/gigaverbo-v2-preferences
|
||||||
|
metrics:
|
||||||
|
- perplexity
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
widget:
|
||||||
|
- text: "<|im_start|>user\nQual é a capital de Portugal?<|im_end|><|im_start|>assistant\n"
|
||||||
|
example_title: Exemplo
|
||||||
|
- text: "<|im_start|>user\nEscreva um poema sobre a floresta amazônica.<|im_end|><|im_start|>assistant\n"
|
||||||
|
example_title: Exemplo
|
||||||
|
- text: "<|im_start|>user\nListe três benefícios da energia solar.<|im_end|><|im_start|>assistant\n"
|
||||||
|
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: 65000
|
||||||
|
source: CodeCarbon
|
||||||
|
training_type: post-training
|
||||||
|
geographical_location: Germany
|
||||||
|
hardware_used: NVIDIA A100-SXM4-80GB
|
||||||
|
model-index:
|
||||||
|
- name: Tucano2-qwen-1.5B-Instruct
|
||||||
|
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: 38.63
|
||||||
|
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: MMLU
|
||||||
|
type: Polygl0t/MMLU-poly
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 41.46
|
||||||
|
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: 62.33
|
||||||
|
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: 40.33
|
||||||
|
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: 53.6
|
||||||
|
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: 40.73
|
||||||
|
name: Acc
|
||||||
|
source:
|
||||||
|
url: https://github.com/eduagarcia/lm-evaluation-harness-pt
|
||||||
|
name: oab_exams
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: IFEval
|
||||||
|
type: Polygl0t/IFEval-PT
|
||||||
|
split: train
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: ifeval_pt_inst_level_loose_acc
|
||||||
|
value: 41.86
|
||||||
|
name: Acc-loose
|
||||||
|
- type: ifeval_pt_prompt_level_loose_acc
|
||||||
|
value: 30.0
|
||||||
|
name: Acc-loose
|
||||||
|
source:
|
||||||
|
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||||
|
name: ifeval_pt
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: GSM8K
|
||||||
|
type: Polygl0t/gsm8k-pt
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: flexible-extract
|
||||||
|
value: 18.49
|
||||||
|
name: Acc-flex
|
||||||
|
source:
|
||||||
|
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||||
|
name: gsm8k_pt
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: HumanEval
|
||||||
|
type: openai/openai_humaneval
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: pass@1
|
||||||
|
value: 26.21
|
||||||
|
name: pass@1
|
||||||
|
source:
|
||||||
|
url: https://github.com/Polygl0t/lm-evaluation-harness
|
||||||
|
base_model: Polygl0t/Tucano2-qwen-1.5B-Base
|
||||||
|
---
|
||||||
|
|
||||||
|
# Tucano2-qwen-1.5B-Instruct
|
||||||
|
|
||||||
|
<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-1.5B-Instruct](https://huggingface.co/Polygl0t/Tucano2-qwen-1.5B-Instruct)** is an instruction-tuned Portuguese language model on top of **Tucano2-qwen-0.5B-Base**. It has been trained using a combination of one round of supervised fine-tuning (SFT) and one round of Anchored Preference Optimization (APO).
|
||||||
|
|
||||||
|
Despite its compact size, the model delivers strong performance across a wide range of Portuguese benchmarks and supports tasks such as **retrieval-augmented generation**, **function calling and tool use**, **summarization**, and **structured output generation**, among others.
|
||||||
|
|
||||||
|
**All datasets, source code, and training recipes used to develop the Tucano2 series are fully open and reproducible.**
|
||||||
|
|
||||||
|
## Details
|
||||||
|
|
||||||
|
- **Architecture:** a Transformer-based model ([`qwen3`](https://huggingface.co/docs/transformers/main/en/model_doc/qwen3))
|
||||||
|
- **Size:** 1,510,073,344 parameters
|
||||||
|
- **Context length:** 4,096 tokens
|
||||||
|
- **Dataset(s):**
|
||||||
|
- [Polygl0t/gigaverbo-v2-sft](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2-sft)
|
||||||
|
- [Polygl0t/gigaverbo-v2-preferences](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2-preferences)
|
||||||
|
- **Training time**: ~ 82 hours
|
||||||
|
- **Emissions:** 65 KgCO2 (Germany)
|
||||||
|
- **Total energy consumption:** 170 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 files:
|
||||||
|
|
||||||
|
- Single stage Supervised Fine-Tuning (linear warmup with cosine decay): [training_config_sft.yaml](training_config_sft.yaml)
|
||||||
|
- Single stage Anchored Preference Optimization (linear warmup with cosine decay): [training_config_apo.yaml](training_config_apo.yaml)
|
||||||
|
- Training Logs (loss, lr, rewards, etc.): [train_logs_apo.parquet](train_logs_apo.parquet), [train_logs_sft.parquet](train_logs_sft.parquet)
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary><b>SFT Loss Curve</b></summary>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary><b>APO Rewards</b></summary>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## Intended Uses
|
||||||
|
|
||||||
|
The primary intended use Tucano2-qwen-1.5B-Instruct is to serve as foundations for research and development involving Portuguese language modeling. You may also fine-tune and adapt Tucano2-qwen-1.5B-Instruct for deployment if your use follows the Apache 2.0 license. If you decide to use Tucano2-qwen-1.5B-Instruct as a basis for your fine-tuned model, please conduct your own risk and bias assessment.
|
||||||
|
|
||||||
|
## Basic usage
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
|
||||||
|
import torch
|
||||||
|
|
||||||
|
# Load model and tokenizer
|
||||||
|
model_id = "Polygl0t/Tucano2-qwen-1.5B-Instruct"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_id,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Configure generation parameters
|
||||||
|
generation_config = GenerationConfig(
|
||||||
|
do_sample=True,
|
||||||
|
temperature=0.1,
|
||||||
|
top_k=50,
|
||||||
|
top_p=1.0,
|
||||||
|
repetition_penalty=1.2,
|
||||||
|
max_new_tokens=150,
|
||||||
|
pad_token_id=tokenizer.eos_token_id,
|
||||||
|
)
|
||||||
|
|
||||||
|
# Prepare chat messages
|
||||||
|
messages = [
|
||||||
|
{"role": "user", "content": "Qual é a capital de Portugal?"}
|
||||||
|
]
|
||||||
|
|
||||||
|
# Apply chat template and generate
|
||||||
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||||
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||||
|
|
||||||
|
with torch.no_grad():
|
||||||
|
outputs = model.generate(**inputs, generation_config=generation_config)
|
||||||
|
|
||||||
|
# Decode and print response
|
||||||
|
response = tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
|
||||||
|
print(f"🤖 {response}")
|
||||||
|
```
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
Like almost all other language models trained on large text datasets scraped from the web, the Tucano2-qwen-1.5B-Instruct 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-1.5B-Instruct is subject to the following:
|
||||||
|
|
||||||
|
- **Hallucinations:** Tucano2-qwen-1.5B-Instruct can produce content that can be mistaken as true facts, but are misleading or entirely false, i.e., hallucination.
|
||||||
|
|
||||||
|
- **Biases and Toxicity:** Tucano2-qwen-1.5B-Instruct 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-1.5B-Instruct 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-1.5B-Instruct 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-1.5B-Instruct is released with a permissive license, we urge users to perform their risk analysis on them if they intend to use them for real-world applications.
|
||||||
|
|
||||||
|
## Evaluations
|
||||||
|
|
||||||
|
The table below compares the Tucano2 (Instruct variant) series against other chat models of similar size. We divide our evaluations into three sets:
|
||||||
|
|
||||||
|
- **Knowledge & Reasoning:** ARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT
|
||||||
|
- **Instruction Following:** IFEval-PT
|
||||||
|
- **Coding:** HumanEval
|
||||||
|
|
||||||
|
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. | Knowledge & Reasoning (NPM) | Instruction Following | Coding |
|
||||||
|
| ------------------------------ | ---------- | --------------------------- | --------------------- | ------ |
|
||||||
|
| **Tucano2-qwen-3.7B-Instruct** | 53.64 | 56.22 | 41.67 | 47.56 |
|
||||||
|
| Jurema-7B | 53.03 | 50.66 | 47 | 75.61 |
|
||||||
|
| Qwen2.5-3B-Instruct | 51.71 | 47.34 | 63.33 | 70.73 |
|
||||||
|
| Qwen3-4B | 51.36 | 42.33 | 79.33 | 86.59 |
|
||||||
|
| Gemma-3-Gaia-PT-BR-4b-it | 49.93 | 45 | 70.33 | 64.02 |
|
||||||
|
| SmolLM3-3B | 49.54 | 43.99 | 69.67 | 68.29 |
|
||||||
|
| Llama-3.2-3B-Instruct | 45.82 | 43.08 | 62.67 | 48.17 |
|
||||||
|
| Qwen2.5-1.5B-Instruct | 41.39 | 40.25 | 42 | 48.78 |
|
||||||
|
| **Tucano2-qwen-1.5B-Instruct** | 37.54 | 39.61 | 34.33 | 26.22 |
|
||||||
|
| Qwen3-1.7B | 36.3 | 28.24 | 65 | 64.02 |
|
||||||
|
| **Tucano2-qwen-0.5B-Instruct** | 26.08 | 27.77 | 30 | 10.37 |
|
||||||
|
| Qwen3-0.6B | 22.21 | 15.13 | 55 | 39.02 |
|
||||||
|
| Llama-3.2-1B-Instruct | 20.14 | 15.37 | 44.33 | 29.27 |
|
||||||
|
| Qwen2.5-0.5B-Instruct | 17.8 | 14.98 | 31 | 24.39 |
|
||||||
|
| Tucano-2b4-Instruct | 3.78 | 2.71 | 15 | 0 |
|
||||||
|
| Tucano-1b1-Instruct | 2.59 | 1.42 | 13.33 | 0 |
|
||||||
|
| TeenyTinyLlama-460m-Chat | 0.07 | -1.68 | 12.33 | 0 |
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary><b>Evaluation Suite</b></summary>
|
||||||
|
|
||||||
|
| **Benchmark** | **n-shot** | **Type** | **Baseline** | **Metric** |
|
||||||
|
| ------------------------- | ---------- | ------------- | ------------ | ------------------------ |
|
||||||
|
| **Knowledge & Reasoning** | | | | |
|
||||||
|
| ARC-Challenge | 5-shot | MC-Q&A | 25 | `acc_norm` |
|
||||||
|
| 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` |
|
||||||
|
| GSM8K-PT | 0-shot | Math Problems | 0 | `flexible-extract` |
|
||||||
|
| **Instruction Following** | | | | |
|
||||||
|
| IFEval-PT | 0-shot | Instruction | 0 | `prompt_level_loose_acc` |
|
||||||
|
| **Coding** | | | | |
|
||||||
|
| HumanEval | 0-shot | Coding | 0 | `pass@1` |
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary><b>Individual Benchmarks</b></summary>
|
||||||
|
|
||||||
|
| | BLUEX | ENEM | OAB | ARC Challenge | BELEBELE | MMLU | IFEval-PT | GSM8K-PT | HumanEval |
|
||||||
|
| ------------------------------ | ----- | ----- | ----- | ------------- | -------- | ----- | --------- | -------- | --------- |
|
||||||
|
| **Tucano2-qwen-3.7B-Instruct** | 64.53 | 72.92 | 54.31 | 60.34 | 85.22 | 64.64 | 41.67 | 53.81 | 47.56 |
|
||||||
|
| Jurema-7B | 63.42 | 70.96 | 64.97 | 52.56 | 88.44 | 49.91 | 47 | 30.29 | 75.61 |
|
||||||
|
| Qwen2.5-3B-Instruct | 56.88 | 68.65 | 46.79 | 41.71 | 84 | 58.22 | 63.33 | 51.9 | 70.73 |
|
||||||
|
| Qwen3-4B | 63.28 | 72.15 | 50.3 | 43.08 | 83.67 | 26.93 | 79.33 | 39.88 | 86.59 |
|
||||||
|
| Gemma-3-Gaia-PT-BR-4b-it | 50.9 | 64.52 | 43.46 | 54.7 | 78.89 | 51.49 | 70.33 | 51.29 | 64.02 |
|
||||||
|
| SmolLM3-3B | 53.55 | 64.73 | 41 | 52.74 | 78.67 | 53.23 | 69.67 | 44.44 | 68.29 |
|
||||||
|
| Llama-3.2-3B-Instruct | 52.02 | 59.13 | 44.97 | 43.93 | 78.56 | 52.14 | 62.67 | 55.1 | 48.17 |
|
||||||
|
| Qwen2.5-1.5B-Instruct | 52.02 | 61.79 | 44.28 | 39.74 | 76 | 51.91 | 42 | 42.16 | 48.78 |
|
||||||
|
| **Tucano2-qwen-1.5B-Instruct** | 52.85 | 62.7 | 43.42 | 50.26 | 77.56 | 52.54 | 34.33 | 19.71 | 26.22 |
|
||||||
|
| Qwen3-1.7B | 50.49 | 58.64 | 32.62 | 36.67 | 64.89 | 30.56 | 65 | 26.94 | 64.02 |
|
||||||
|
| **Tucano2-qwen-0.5B-Instruct** | 40.33 | 53.6 | 40.73 | 38.63 | 62.33 | 41.46 | 30 | 18.49 | 10.37 |
|
||||||
|
| Qwen3-0.6B | 34.91 | 41.15 | 29.75 | 30.51 | 37.11 | 26.48 | 55 | 31.66 | 39.02 |
|
||||||
|
| Llama-3.2-1B-Instruct | 30.04 | 34.01 | 30.84 | 32.82 | 41.56 | 35.15 | 44.33 | 26.56 | 29.27 |
|
||||||
|
| Qwen2.5-0.5B-Instruct | 30.18 | 34.08 | 29.34 | 27.44 | 50.67 | 39.54 | 31 | 14.69 | 24.39 |
|
||||||
|
| Tucano-2b4-Instruct | 25.87 | 20.01 | 26.74 | 31.97 | 24 | 26.72 | 15 | 2.05 | 0 |
|
||||||
|
| Tucano-1b1-Instruct | 22.95 | 19.94 | 25.33 | 30 | 24.89 | 25.59 | 13.33 | 1.67 | 0 |
|
||||||
|
| TeenyTinyLlama-460m-Chat | 17.25 | 18.19 | 19.73 | 26.84 | 22.89 | 26.97 | 12.33 | 2.05 | 0 |
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary><b>Inference Samples on Various Tasks</b></summary>
|
||||||
|
|
||||||
|
### Math
|
||||||
|
|
||||||
|
**Prompt:**
|
||||||
|
|
||||||
|
<|im_start|>user
|
||||||
|
Como eu posso resolver o seguinte problema: 2x + 3 = 11?<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
|
||||||
|
**Response:**
|
||||||
|
|
||||||
|
Para encontrar a solução para esta equação, você precisa isolar x. Primeiro subtraia 3 de ambos os lados da equação e depois divida por 2. A resposta é x=4. Para verificar sua resposta substitua 4 na equação original (2 * 4) + 3 = 11, que simplifica para 8 + 3 = 11. Portanto, a solução está correta .<|im_end|>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Structured Output
|
||||||
|
|
||||||
|
**Prompt:**
|
||||||
|
|
||||||
|
<|im_start|>system
|
||||||
|
Sempre responda em formato JSON estruturado conforme solicitado.<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
Extraia e resuma as informações principais do e-mail abaixo. Escreva sua resposta (em formato JSON) contendo as seguintes chaves: 'assunto', 'remetente', 'destinatário', 'resumo'. Aqui está o e-mail:
|
||||||
|
|
||||||
|
Assunto: RE: Atualização sobre o Projeto de Conservação de Bacias Hidrográfica
|
||||||
|
|
||||||
|
Carlos,
|
||||||
|
|
||||||
|
Obrigado por enviar o currículo atualizado. Tive a oportunidade de revisá-lo e achei que ficou ótimo! Você fez um excelente trabalho ao tornar as informações acessíveis e envolventes para uma ampla audiência.
|
||||||
|
|
||||||
|
Em relação à possível resistência dos membros da comunidade, concordo que devemos estar preparados para abordar suas preocupações. Uma ideia que tive foi incluir alguns exemplos práticos de como o uso indevido das águas no rio Amazonas ou na Baía de Guanabara e o descarte incorreto de resíduos sólidos têm prejudicado essas áreas. Ouvi-los falar diretamente sobre as consequências pode ser muito mais persuasivo do que simplesmente mostrar dados estatísticos.
|
||||||
|
|
||||||
|
Além disso, também considero importante destacarmos os ganhos econômicos trazidos pela adoção de práticas mais sustentáveis, como tarifas de água menores e gastos diminutos relacionados à limpeza urbana. No final das contas, as pessoas costumam responder bem quando veem vantagens tangíveis além dos aspectos puramente ambientais.
|
||||||
|
|
||||||
|
Diga-me o que você pensa dessas sugestões! Ficarei contente em ajudar a desenvolver ainda mais estratégias para vencer essa resistência e engajar as pessoas nessa nossa jornada.
|
||||||
|
|
||||||
|
Atenciosamente,
|
||||||
|
Helena<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
|
||||||
|
**Response:**
|
||||||
|
|
||||||
|
```json
|
||||||
|
|
||||||
|
{
|
||||||
|
"assunto": "RE: Atualização sobre o Projeto de Conservação de Bacias Hidrográficas",
|
||||||
|
"remetente": "Helena",
|
||||||
|
"destinatario": "Carlos",
|
||||||
|
"resumo": "A remetente elogia o novo currículo enviado pelo destinatário, sugerindo adicionar casos reais impactantes nas bacias hidrográficas brasileiras para aumentar a eficácia educacional. Ela enfatiza a importância de evidenciar benefícios financeiros associados às práticas sustentáveis."
|
||||||
|
}
|
||||||
|
|
||||||
|
```<|im_end|>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Function Call / Tool Use
|
||||||
|
|
||||||
|
**Prompt:**
|
||||||
|
|
||||||
|
<|im_start|>system
|
||||||
|
Utilize as ferramentas para resolver as tarefas que o usuário lhe solicitar. Se as ferramentas forem insuficientes, explique ao usuário que não é possível completar a tarefa.
|
||||||
|
|
||||||
|
\# Tools / Ferramentas
|
||||||
|
|
||||||
|
Você pode chamar uma ou mais funções para auxiliar na consulta do usuário.
|
||||||
|
|
||||||
|
Você recebe assinaturas de funções dentro de tags XML <tools></tools>:
|
||||||
|
<tools>
|
||||||
|
{"type": "function", "function": {"name": "create_todo", "description": "Cria uma nova tarefa no aplicativo de todo.", "parameters": {"type": "object", "properties": {"task_description": {"type": "string", "description": "Descrição da tarefa a ser criada."}, "due_date": {"type": "string", "description": "Data de entrega da tarefa no formato YYYY-MM-DD."}}, "required": ["task_description", "due_date"]}}}
|
||||||
|
</tools>
|
||||||
|
|
||||||
|
Para cada chamada de função, retorne um objeto json com o nome da função e os argumentos dentro das tags XML <tool_call></tool_call>:
|
||||||
|
<tool_call>
|
||||||
|
{"name": <function-name>, "arguments": <args-json-object>}
|
||||||
|
</tool_call><|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
Eu preciso criar uma nova tarefa para o meu projeto.<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
Claro, eu posso ajudar com isso. Você poderia, por favor, me fornecer a descrição da tarefa e a data de entrega?<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
A tarefa é finalizar o relatório do projeto e a data de entrega é 2022-03-15.<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
|
||||||
|
**Response:**
|
||||||
|
|
||||||
|
<tool_call>
|
||||||
|
{"name": "create_todo", "arguments": {"task_description": "Finalizing the project report", "due_date": "2022-03-15"}}
|
||||||
|
</tool_call><|im_end|>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Similarity Scoring
|
||||||
|
|
||||||
|
**Prompt:**
|
||||||
|
|
||||||
|
<|im_start|>user
|
||||||
|
Frase 1: O artista pintou um quadro inspirado nos campos floridos da primavera.
|
||||||
|
Frase 2: O criador produziu uma obra que representava paisagens urbanas cinzentas.
|
||||||
|
Pergunta: Qu\u00e3o similares s\u00e3o as duas frases? D\u00ea uma pontua\u00e7\u00e3o entre 1,0 a 5,0.
|
||||||
|
Resposta:<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
|
||||||
|
**Response:**
|
||||||
|
|
||||||
|
2.5. As duas frases apresentam situações diferentes quanto à temática e estilo artístico, resultando numa pontuação média de similaridade de 2.5, indicando pouca relação entre elas.<|im_end|>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Classification
|
||||||
|
|
||||||
|
**Prompt:**
|
||||||
|
|
||||||
|
<|im_start|>user
|
||||||
|
Classifique o sentimento da seguinte resenha de filme como 'Positiva', 'Negativa' ou 'Neutra':
|
||||||
|
|
||||||
|
"O filme foi uma experiência cinematográfica incrível, com atuações excepcionais e uma trama envolvente que me manteve na ponta da cadeira do começo ao fim."<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
|
||||||
|
**Response:**
|
||||||
|
|
||||||
|
Sentimento: Positivo. A crítica destaca aspectos positivos como performances excelentes e um enredo cativante, indicando uma opinião favorável sobre o filme.<|im_end|>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
Below, we compare the performance of Tucano2-qwen-1.5B-Instruct with Qwen3-1.7B, a strong baseline in the 1.5B parameter range. The percentages represent the absolute difference in performance between the two models on each benchmark. All other plots can be found in the [.plots](https://huggingface.co/Polygl0t/Tucano2-qwen-1.5B-Instruct/tree/main/.plots/) folder.
|
||||||
|
|
||||||
|
**Tucano2-qwen-1.5B-Instruct vs Qwen3-1.7B**
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## 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-1.5B-Instruct is licensed under the Apache License, Version 2.0. For more details, see the [LICENSE](LICENSE) file.
|
||||||
83
chat_template.jinja
Normal file
83
chat_template.jinja
Normal file
@@ -0,0 +1,83 @@
|
|||||||
|
{#- Handle tool/function calling setup #}
|
||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{#- Include system message if present #}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{#- Add tool calling instructions in Portuguese #}
|
||||||
|
{{- "# Tools / Ferramentas\n\nVocê pode chamar uma ou mais funções para auxiliar na consulta do usuário.\n\nVocê recebe assinaturas de funções dentro de tags XML <tools></tools>:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nPara cada chamada de função, retorne um objeto json com o nome da função e os argumentos dentro das tags XML <tool_call></tool_call>:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{#- Standard system message without tools #}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- Process each message in the conversation #}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{#- Normalize content to string #}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- Handle user messages and non-first system messages #}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
|
||||||
|
{#- Handle assistant messages without reasoning #}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role }}
|
||||||
|
{% generation %}
|
||||||
|
{{- content }}
|
||||||
|
|
||||||
|
{#- Add tool calls if present #}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{#- Normalize tool call format #}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>' }}
|
||||||
|
{% endgeneration %}
|
||||||
|
|
||||||
|
{#- Handle tool response messages #}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{#- Group consecutive tool responses under one user message #}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
|
||||||
|
{#- Add generation prompt if requested #}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- endif %}
|
||||||
61
config.json
Normal file
61
config.json
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
{
|
||||||
|
"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": 2048,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 6144,
|
||||||
|
"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"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 4096,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"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,
|
||||||
|
"transformers_version": "4.57.3",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 49152
|
||||||
|
}
|
||||||
207
evals.yaml
Normal file
207
evals.yaml
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
evaluations:
|
||||||
|
arc_challenge_poly_pt_acc: 0.47094017094017093
|
||||||
|
arc_challenge_poly_pt_acc_norm: 0.5025641025641026
|
||||||
|
arc_challenge_poly_pt_acc_norm_stderr: 0.014623692220064299
|
||||||
|
arc_challenge_poly_pt_acc_stderr: 0.014599164650716437
|
||||||
|
arc_challenge_poly_pt_alias: arc_challenge_poly_pt
|
||||||
|
assin2_rte_acc,all: 0.9178921568627451
|
||||||
|
assin2_rte_acc_stderr,all: 0.0039410227425137
|
||||||
|
assin2_rte_alias: assin2_rte
|
||||||
|
assin2_rte_f1_macro,all: 0.9176110196232412
|
||||||
|
assin2_rte_f1_macro_stderr,all: 0.003955066154708788
|
||||||
|
assin2_sts_alias: assin2_sts
|
||||||
|
assin2_sts_mse,all: 0.8036356209150326
|
||||||
|
assin2_sts_mse_stderr,all: N/A
|
||||||
|
assin2_sts_pearson,all: 0.7335010773330974
|
||||||
|
assin2_sts_pearson_stderr,all: 0.006813537226494434
|
||||||
|
assin_entailment_acc: 0.6955
|
||||||
|
assin_entailment_acc_stderr: 0.007277236909999638
|
||||||
|
assin_entailment_alias: assin_entailment
|
||||||
|
assin_paraphrase_acc: 0.677
|
||||||
|
assin_paraphrase_acc_stderr: 0.007394688658428343
|
||||||
|
assin_paraphrase_alias: assin_paraphrase
|
||||||
|
belebele_por_Latn_acc: 0.7755555555555556
|
||||||
|
belebele_por_Latn_acc_norm: 0.7755555555555556
|
||||||
|
belebele_por_Latn_acc_norm_stderr: 0.013914930474237296
|
||||||
|
belebele_por_Latn_acc_stderr: 0.013914930474237296
|
||||||
|
belebele_por_Latn_alias: belebele_por_Latn
|
||||||
|
bluex_acc,all: 0.5285118219749653
|
||||||
|
bluex_acc,exam_id__UNICAMP_2018: 0.5185185185185185
|
||||||
|
bluex_acc,exam_id__UNICAMP_2019: 0.44
|
||||||
|
bluex_acc,exam_id__UNICAMP_2020: 0.509090909090909
|
||||||
|
bluex_acc,exam_id__UNICAMP_2021_1: 0.4782608695652174
|
||||||
|
bluex_acc,exam_id__UNICAMP_2021_2: 0.47058823529411764
|
||||||
|
bluex_acc,exam_id__UNICAMP_2022: 0.6410256410256411
|
||||||
|
bluex_acc,exam_id__UNICAMP_2023: 0.6046511627906976
|
||||||
|
bluex_acc,exam_id__UNICAMP_2024: 0.5333333333333333
|
||||||
|
bluex_acc,exam_id__USP_2018: 0.4074074074074074
|
||||||
|
bluex_acc,exam_id__USP_2019: 0.5
|
||||||
|
bluex_acc,exam_id__USP_2020: 0.6071428571428571
|
||||||
|
bluex_acc,exam_id__USP_2021: 0.5384615384615384
|
||||||
|
bluex_acc,exam_id__USP_2022: 0.42857142857142855
|
||||||
|
bluex_acc,exam_id__USP_2023: 0.6818181818181818
|
||||||
|
bluex_acc,exam_id__USP_2024: 0.6341463414634146
|
||||||
|
bluex_acc_stderr,all: 0.010703918286665611
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2018: 0.03937226593136202
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2019: 0.0404309855509269
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2020: 0.0389358045204499
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2021_1: 0.04241243284078559
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2021_2: 0.04027645736401125
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2022: 0.044230892510041545
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2023: 0.04301638178039838
|
||||||
|
bluex_acc_stderr,exam_id__UNICAMP_2024: 0.04292586445321273
|
||||||
|
bluex_acc_stderr,exam_id__USP_2018: 0.0385530737645887
|
||||||
|
bluex_acc_stderr,exam_id__USP_2019: 0.04559218480567802
|
||||||
|
bluex_acc_stderr,exam_id__USP_2020: 0.03761017438804557
|
||||||
|
bluex_acc_stderr,exam_id__USP_2021: 0.04001597061911072
|
||||||
|
bluex_acc_stderr,exam_id__USP_2022: 0.04070596417180048
|
||||||
|
bluex_acc_stderr,exam_id__USP_2023: 0.040428408321166086
|
||||||
|
bluex_acc_stderr,exam_id__USP_2024: 0.04340314503826957
|
||||||
|
bluex_alias: bluex
|
||||||
|
calame_pt_acc: 0.5438342967244701
|
||||||
|
calame_pt_acc_stderr: 0.010934163426897668
|
||||||
|
calame_pt_alias: calame_pt
|
||||||
|
calame_pt_perplexity: 7.8689968011124725
|
||||||
|
calame_pt_perplexity_stderr: 0.41766365172631903
|
||||||
|
enem_challenge_acc,all: 0.6270118964310707
|
||||||
|
enem_challenge_acc,exam_id__2009: 0.6347826086956522
|
||||||
|
enem_challenge_acc,exam_id__2010: 0.6752136752136753
|
||||||
|
enem_challenge_acc,exam_id__2011: 0.6923076923076923
|
||||||
|
enem_challenge_acc,exam_id__2012: 0.6379310344827587
|
||||||
|
enem_challenge_acc,exam_id__2013: 0.6111111111111112
|
||||||
|
enem_challenge_acc,exam_id__2014: 0.6330275229357798
|
||||||
|
enem_challenge_acc,exam_id__2015: 0.5462184873949579
|
||||||
|
enem_challenge_acc,exam_id__2016: 0.6198347107438017
|
||||||
|
enem_challenge_acc,exam_id__2016_2: 0.6097560975609756
|
||||||
|
enem_challenge_acc,exam_id__2017: 0.6120689655172413
|
||||||
|
enem_challenge_acc,exam_id__2022: 0.5939849624060151
|
||||||
|
enem_challenge_acc,exam_id__2023: 0.6592592592592592
|
||||||
|
enem_challenge_acc_stderr,all: 0.0073957026155519546
|
||||||
|
enem_challenge_acc_stderr,exam_id__2009: 0.025965719340461144
|
||||||
|
enem_challenge_acc_stderr,exam_id__2010: 0.02502188604536942
|
||||||
|
enem_challenge_acc_stderr,exam_id__2011: 0.02467006930960307
|
||||||
|
enem_challenge_acc_stderr,exam_id__2012: 0.025714191658261398
|
||||||
|
enem_challenge_acc_stderr,exam_id__2013: 0.02702908679710427
|
||||||
|
enem_challenge_acc_stderr,exam_id__2014: 0.026672592927520465
|
||||||
|
enem_challenge_acc_stderr,exam_id__2015: 0.02626461947663519
|
||||||
|
enem_challenge_acc_stderr,exam_id__2016: 0.025564903994126094
|
||||||
|
enem_challenge_acc_stderr,exam_id__2016_2: 0.025424569351359966
|
||||||
|
enem_challenge_acc_stderr,exam_id__2017: 0.026108373622566433
|
||||||
|
enem_challenge_acc_stderr,exam_id__2022: 0.024621347603181173
|
||||||
|
enem_challenge_acc_stderr,exam_id__2023: 0.023527643017571674
|
||||||
|
enem_challenge_alias: enem
|
||||||
|
faquad_nli_acc,all: 0.8584615384615385
|
||||||
|
faquad_nli_acc_stderr,all: 0.009630496129889232
|
||||||
|
faquad_nli_alias: faquad_nli
|
||||||
|
faquad_nli_f1_macro,all: 0.7762511973180077
|
||||||
|
faquad_nli_f1_macro_stderr,all: 0.014629139687819745
|
||||||
|
global_piqa_completions_por_latn_braz_acc: 0.75
|
||||||
|
global_piqa_completions_por_latn_braz_acc_bytes: 0.7
|
||||||
|
global_piqa_completions_por_latn_braz_acc_bytes_stderr: 0.04605661864718383
|
||||||
|
global_piqa_completions_por_latn_braz_acc_norm: 0.71
|
||||||
|
global_piqa_completions_por_latn_braz_acc_norm_stderr: 0.045604802157206865
|
||||||
|
global_piqa_completions_por_latn_braz_acc_stderr: 0.04351941398892446
|
||||||
|
global_piqa_completions_por_latn_braz_alias: global_piqa_completions_por_latn_braz
|
||||||
|
gsm8k_pt_alias: gsm8k_pt
|
||||||
|
gsm8k_pt_exact_match,flexible-extract: 0.19710806697108066
|
||||||
|
gsm8k_pt_exact_match,strict-match: 0.0
|
||||||
|
gsm8k_pt_exact_match_stderr,flexible-extract: 0.010978635935133022
|
||||||
|
gsm8k_pt_exact_match_stderr,strict-match: 0.0
|
||||||
|
hatebr_offensive_acc,all: 0.805
|
||||||
|
hatebr_offensive_acc_stderr,all: 0.00750545853190643
|
||||||
|
hatebr_offensive_alias: hatebr_offensive_binary
|
||||||
|
hatebr_offensive_f1_macro,all: 0.7986300308904273
|
||||||
|
hatebr_offensive_f1_macro_stderr,all: 0.007718372444189955
|
||||||
|
hellaswag_poly_pt_acc: 0.43222450969769205
|
||||||
|
hellaswag_poly_pt_acc_norm: 0.5524975620327229
|
||||||
|
hellaswag_poly_pt_acc_norm_stderr: 0.00517617669289931
|
||||||
|
hellaswag_poly_pt_acc_stderr: 0.005156906089879843
|
||||||
|
hellaswag_poly_pt_alias: hellaswag_poly_pt
|
||||||
|
humaneval_instruct_alias: humaneval_instruct
|
||||||
|
humaneval_instruct_pass@1,create_test: 0.2621951219512195
|
||||||
|
humaneval_instruct_pass@1_stderr,create_test: 0.03445000289173463
|
||||||
|
ifeval_pt_alias: ifeval_pt
|
||||||
|
ifeval_pt_inst_level_loose_acc: 0.46511627906976744
|
||||||
|
ifeval_pt_inst_level_loose_acc_stderr: N/A
|
||||||
|
ifeval_pt_inst_level_strict_acc: 0.4232558139534884
|
||||||
|
ifeval_pt_inst_level_strict_acc_stderr: N/A
|
||||||
|
ifeval_pt_prompt_level_loose_acc: 0.3433333333333333
|
||||||
|
ifeval_pt_prompt_level_loose_acc_stderr: 0.027459642357098978
|
||||||
|
ifeval_pt_prompt_level_strict_acc: 0.30333333333333334
|
||||||
|
ifeval_pt_prompt_level_strict_acc_stderr: 0.026585019936500975
|
||||||
|
lambada_poly_pt_acc: 0.5905297884727343
|
||||||
|
lambada_poly_pt_acc_stderr: 0.006850844880897535
|
||||||
|
lambada_poly_pt_alias: lambada_poly_pt
|
||||||
|
lambada_poly_pt_perplexity: 9.837299391644223
|
||||||
|
lambada_poly_pt_perplexity_stderr: 0.3695848037190668
|
||||||
|
mmlu_poly_pt_acc: 0.5254428099669769
|
||||||
|
mmlu_poly_pt_acc_stderr: 0.0043261940110685525
|
||||||
|
mmlu_poly_pt_alias: mmlu_poly_pt
|
||||||
|
oab_exams_acc,all: 0.43416856492027334
|
||||||
|
oab_exams_acc,exam_id__2010-01: 0.3411764705882353
|
||||||
|
oab_exams_acc,exam_id__2010-02: 0.46
|
||||||
|
oab_exams_acc,exam_id__2011-03: 0.3838383838383838
|
||||||
|
oab_exams_acc,exam_id__2011-04: 0.4
|
||||||
|
oab_exams_acc,exam_id__2011-05: 0.5
|
||||||
|
oab_exams_acc,exam_id__2012-06: 0.4125
|
||||||
|
oab_exams_acc,exam_id__2012-06a: 0.425
|
||||||
|
oab_exams_acc,exam_id__2012-07: 0.425
|
||||||
|
oab_exams_acc,exam_id__2012-08: 0.4625
|
||||||
|
oab_exams_acc,exam_id__2012-09: 0.38961038961038963
|
||||||
|
oab_exams_acc,exam_id__2013-10: 0.5
|
||||||
|
oab_exams_acc,exam_id__2013-11: 0.575
|
||||||
|
oab_exams_acc,exam_id__2013-12: 0.475
|
||||||
|
oab_exams_acc,exam_id__2014-13: 0.425
|
||||||
|
oab_exams_acc,exam_id__2014-14: 0.475
|
||||||
|
oab_exams_acc,exam_id__2014-15: 0.5
|
||||||
|
oab_exams_acc,exam_id__2015-16: 0.425
|
||||||
|
oab_exams_acc,exam_id__2015-17: 0.4230769230769231
|
||||||
|
oab_exams_acc,exam_id__2015-18: 0.4
|
||||||
|
oab_exams_acc,exam_id__2016-19: 0.47435897435897434
|
||||||
|
oab_exams_acc,exam_id__2016-20: 0.4625
|
||||||
|
oab_exams_acc,exam_id__2016-20a: 0.375
|
||||||
|
oab_exams_acc,exam_id__2016-21: 0.4125
|
||||||
|
oab_exams_acc,exam_id__2017-22: 0.4375
|
||||||
|
oab_exams_acc,exam_id__2017-23: 0.3375
|
||||||
|
oab_exams_acc,exam_id__2017-24: 0.425
|
||||||
|
oab_exams_acc,exam_id__2018-25: 0.4125
|
||||||
|
oab_exams_acc_stderr,all: 0.006102155835634948
|
||||||
|
oab_exams_acc_stderr,exam_id__2010-01: 0.029640791842627794
|
||||||
|
oab_exams_acc_stderr,exam_id__2010-02: 0.02872289890111472
|
||||||
|
oab_exams_acc_stderr,exam_id__2011-03: 0.02813693132118459
|
||||||
|
oab_exams_acc_stderr,exam_id__2011-04: 0.03154240021693644
|
||||||
|
oab_exams_acc_stderr,exam_id__2011-05: 0.03224120715021378
|
||||||
|
oab_exams_acc_stderr,exam_id__2012-06: 0.031634579715402525
|
||||||
|
oab_exams_acc_stderr,exam_id__2012-06a: 0.031920386806255
|
||||||
|
oab_exams_acc_stderr,exam_id__2012-07: 0.03196335345646489
|
||||||
|
oab_exams_acc_stderr,exam_id__2012-08: 0.03218895689579674
|
||||||
|
oab_exams_acc_stderr,exam_id__2012-09: 0.0320702088032968
|
||||||
|
oab_exams_acc_stderr,exam_id__2013-10: 0.032306001943973275
|
||||||
|
oab_exams_acc_stderr,exam_id__2013-11: 0.03198130854191419
|
||||||
|
oab_exams_acc_stderr,exam_id__2013-12: 0.03227420874356609
|
||||||
|
oab_exams_acc_stderr,exam_id__2014-13: 0.03197697369553699
|
||||||
|
oab_exams_acc_stderr,exam_id__2014-14: 0.03231427645661526
|
||||||
|
oab_exams_acc_stderr,exam_id__2014-15: 0.03281148582087051
|
||||||
|
oab_exams_acc_stderr,exam_id__2015-16: 0.03193036659905079
|
||||||
|
oab_exams_acc_stderr,exam_id__2015-17: 0.03231882364931395
|
||||||
|
oab_exams_acc_stderr,exam_id__2015-18: 0.031606839641845616
|
||||||
|
oab_exams_acc_stderr,exam_id__2016-19: 0.03261356291633692
|
||||||
|
oab_exams_acc_stderr,exam_id__2016-20: 0.03217012301961201
|
||||||
|
oab_exams_acc_stderr,exam_id__2016-20a: 0.03124902402233319
|
||||||
|
oab_exams_acc_stderr,exam_id__2016-21: 0.03172689133529826
|
||||||
|
oab_exams_acc_stderr,exam_id__2017-22: 0.03202936221429109
|
||||||
|
oab_exams_acc_stderr,exam_id__2017-23: 0.03052924311679464
|
||||||
|
oab_exams_acc_stderr,exam_id__2017-24: 0.031892680920180556
|
||||||
|
oab_exams_acc_stderr,exam_id__2018-25: 0.03181646004259634
|
||||||
|
oab_exams_alias: oab_exams
|
||||||
|
portuguese_hate_speech_acc,all: 0.7708578143360753
|
||||||
|
portuguese_hate_speech_acc_stderr,all: 0.010179285936061107
|
||||||
|
portuguese_hate_speech_alias: portuguese_hate_speech_binary
|
||||||
|
portuguese_hate_speech_f1_macro,all: 0.7383400530746562
|
||||||
|
portuguese_hate_speech_f1_macro_stderr,all: 0.011391910083076176
|
||||||
|
tweetsentbr_acc,all: 0.663681592039801
|
||||||
|
tweetsentbr_acc_stderr,all: 0.007468862153058396
|
||||||
|
tweetsentbr_alias: tweetsentbr
|
||||||
|
tweetsentbr_f1_macro,all: 0.57818681435807
|
||||||
|
tweetsentbr_f1_macro_stderr,all: 0.007796495757272563
|
||||||
|
step: 69750
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
2
|
||||||
|
],
|
||||||
|
"max_new_tokens": 1024,
|
||||||
|
"pad_token_id": 49109,
|
||||||
|
"renormalize_logits": true,
|
||||||
|
"repetition_penalty": 1.2,
|
||||||
|
"temperature": 0.1,
|
||||||
|
"transformers_version": "4.57.3",
|
||||||
|
"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.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9772aa3957a766b6103eeed6f240041b79a2a4df31f6ea86f688cd67b2a7bc44
|
||||||
|
size 3020182248
|
||||||
82
ruler.yaml
Normal file
82
ruler.yaml
Normal file
@@ -0,0 +1,82 @@
|
|||||||
|
model_name: Tucano2-qwen-1.5B-Instruct
|
||||||
|
results:
|
||||||
|
niah_pt_multikey_1_1024: 0.556
|
||||||
|
niah_pt_multikey_1_1024_stderr: 0.022242244375731048
|
||||||
|
niah_pt_multikey_1_2048: 0.572
|
||||||
|
niah_pt_multikey_1_2048_stderr: 0.022149790663861947
|
||||||
|
niah_pt_multikey_1_4096: 0.504
|
||||||
|
niah_pt_multikey_1_4096_stderr: N/A
|
||||||
|
niah_pt_multikey_1_alias: " - niah_pt_multikey_1"
|
||||||
|
niah_pt_multikey_2_1024: 0.582
|
||||||
|
niah_pt_multikey_2_1024_stderr: 0.022080014812228193
|
||||||
|
niah_pt_multikey_2_2048: 0.372
|
||||||
|
niah_pt_multikey_2_2048_stderr: 0.021637197985722334
|
||||||
|
niah_pt_multikey_2_4096: 0.132
|
||||||
|
niah_pt_multikey_2_4096_stderr: N/A
|
||||||
|
niah_pt_multikey_2_alias: " - niah_pt_multikey_2"
|
||||||
|
niah_pt_multikey_3_1024: 0.688
|
||||||
|
niah_pt_multikey_3_1024_stderr: 0.020740596536488017
|
||||||
|
niah_pt_multikey_3_2048: 0.496
|
||||||
|
niah_pt_multikey_3_2048_stderr: 0.022382357781962105
|
||||||
|
niah_pt_multikey_3_4096: 0.208
|
||||||
|
niah_pt_multikey_3_4096_stderr: N/A
|
||||||
|
niah_pt_multikey_3_alias: " - niah_pt_multikey_3"
|
||||||
|
niah_pt_multiquery_1024: 0.5075
|
||||||
|
niah_pt_multiquery_1024_stderr: 0.014319483062959385
|
||||||
|
niah_pt_multiquery_2048: 0.445
|
||||||
|
niah_pt_multiquery_2048_stderr: 0.014312921415241465
|
||||||
|
niah_pt_multiquery_4096: 0.3605
|
||||||
|
niah_pt_multiquery_4096_stderr: N/A
|
||||||
|
niah_pt_multiquery_alias: " - niah_pt_multiquery"
|
||||||
|
niah_pt_multivalue_1024: 0.3765
|
||||||
|
niah_pt_multivalue_1024_stderr: 0.015089761489288265
|
||||||
|
niah_pt_multivalue_2048: 0.352
|
||||||
|
niah_pt_multivalue_2048_stderr: 0.014443310508220534
|
||||||
|
niah_pt_multivalue_4096: 0.3525
|
||||||
|
niah_pt_multivalue_4096_stderr: N/A
|
||||||
|
niah_pt_multivalue_alias: " - niah_pt_multivalue"
|
||||||
|
niah_pt_single_1_1024: 0.658
|
||||||
|
niah_pt_single_1_1024_stderr: 0.021236147199899316
|
||||||
|
niah_pt_single_1_2048: 0.578
|
||||||
|
niah_pt_single_1_2048_stderr: 0.022109039310618563
|
||||||
|
niah_pt_single_1_4096: 0.476
|
||||||
|
niah_pt_single_1_4096_stderr: N/A
|
||||||
|
niah_pt_single_1_alias: " - niah_pt_single_1"
|
||||||
|
niah_pt_single_2_1024: 0.452
|
||||||
|
niah_pt_single_2_1024_stderr: 0.022279694107843542
|
||||||
|
niah_pt_single_2_2048: 0.496
|
||||||
|
niah_pt_single_2_2048_stderr: 0.022382357781962105
|
||||||
|
niah_pt_single_2_4096: 0.478
|
||||||
|
niah_pt_single_2_4096_stderr: N/A
|
||||||
|
niah_pt_single_2_alias: " - niah_pt_single_2"
|
||||||
|
niah_pt_single_3_1024: 0.464
|
||||||
|
niah_pt_single_3_1024_stderr: 0.022324981738385333
|
||||||
|
niah_pt_single_3_2048: 0.488
|
||||||
|
niah_pt_single_3_2048_stderr: 0.022376626797927058
|
||||||
|
niah_pt_single_3_4096: 0.502
|
||||||
|
niah_pt_single_3_4096_stderr: N/A
|
||||||
|
niah_pt_single_3_alias: " - niah_pt_single_3"
|
||||||
|
ruler_pt_4096: 0.4209333333333333
|
||||||
|
ruler_pt_4096_stderr: N/A
|
||||||
|
ruler_pt_alias: ruler_pt
|
||||||
|
ruler_pt_cwe_1024: 0.2336
|
||||||
|
ruler_pt_cwe_1024_stderr: 0.007601160126621533
|
||||||
|
ruler_pt_cwe_2048: 0.0674
|
||||||
|
ruler_pt_cwe_2048_stderr: 0.0035916960563391557
|
||||||
|
ruler_pt_cwe_4096: 0.24180000000000001
|
||||||
|
ruler_pt_cwe_4096_stderr: N/A
|
||||||
|
ruler_pt_cwe_alias: " - ruler_pt_cwe"
|
||||||
|
ruler_pt_fwe_1024: 0.8326666666666667
|
||||||
|
ruler_pt_fwe_1024_stderr: 0.010739688265042091
|
||||||
|
ruler_pt_fwe_2048: 0.6426666666666666
|
||||||
|
ruler_pt_fwe_2048_stderr: 0.010748185494645086
|
||||||
|
ruler_pt_fwe_4096: 0.5346666666666666
|
||||||
|
ruler_pt_fwe_4096_stderr: N/A
|
||||||
|
ruler_pt_fwe_alias: " - ruler_pt_fwe"
|
||||||
|
ruler_pt_vt_1024: 0.9568
|
||||||
|
ruler_pt_vt_1024_stderr: 0.0061337399301781715
|
||||||
|
ruler_pt_vt_2048: 0.9288
|
||||||
|
ruler_pt_vt_2048_stderr: 0.007954096762714245
|
||||||
|
ruler_pt_vt_4096: 0.8408
|
||||||
|
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_apo.parquet
Normal file
3
train_logs_apo.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:35e9207c3df27ba4214f3d2d32d081abf0f68425ca32a5d76af3c119e2887b04
|
||||||
|
size 89256
|
||||||
3
train_logs_sft.parquet
Normal file
3
train_logs_sft.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ac674e2a7510d9cc855d1c3252b14e891fb20cbcd252f6a935d4bf2dbf226ba6
|
||||||
|
size 1324274
|
||||||
102
training_config_apo.yaml
Normal file
102
training_config_apo.yaml
Normal file
@@ -0,0 +1,102 @@
|
|||||||
|
# Directory settings
|
||||||
|
checkpoint_dir: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Instruct"
|
||||||
|
train_dataset_dir:
|
||||||
|
# Total: 28,437 samples (x5 epochs)
|
||||||
|
# Harmfull samples (without reasoning): 4,267 samples
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-dpo/harmfull-no-reasoning
|
||||||
|
# Harmfull samples (with reasoning, stripped): 4,008 samples
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-dpo/harmfull-reasoning-stripped
|
||||||
|
# Harmless samples (without reasoning): 10,521 samples
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-dpo/harmless-no-reasoning
|
||||||
|
# Harmless samples (with reasoning, stripped): 9,641 samples
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-dpo/harmless-reasoning-stripped
|
||||||
|
val_dataset_dir: null
|
||||||
|
dataset_type: "jsonl"
|
||||||
|
cache_dir: "/lustre/mlnvme/data/polyglot/.cache"
|
||||||
|
|
||||||
|
# Data loading settings
|
||||||
|
pin_memory: true
|
||||||
|
num_workers_for_dataloader: 16
|
||||||
|
shuffle_dataset: true
|
||||||
|
mask_eos_token: false
|
||||||
|
mask_pad_token: false
|
||||||
|
|
||||||
|
# Model architecture settings
|
||||||
|
vocab_size: 49152
|
||||||
|
num_hidden_layers: 28
|
||||||
|
num_attention_heads: 16
|
||||||
|
num_key_value_heads: 8
|
||||||
|
head_dim: 128
|
||||||
|
hidden_size: 2048
|
||||||
|
intermediate_size: 6144
|
||||||
|
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: 524288
|
||||||
|
micro_batch_size: 4
|
||||||
|
gradient_accumulation_steps: 4
|
||||||
|
eval_micro_batch_size: null
|
||||||
|
num_train_epochs: 5
|
||||||
|
warmup_ratio: 0.1
|
||||||
|
max_learning_rate: 0.000005
|
||||||
|
min_learning_rate: 0.0
|
||||||
|
muon_learning_rate: null
|
||||||
|
weight_decay: 0.0
|
||||||
|
beta1: 0.9
|
||||||
|
beta2: 0.95
|
||||||
|
eps: 0.00000001
|
||||||
|
lr_decay_type: "cosine"
|
||||||
|
use_sqrt: false
|
||||||
|
lr_decay_iters_coef: 1.
|
||||||
|
seed: 42
|
||||||
|
max_steps: 1115
|
||||||
|
max_grad_norm: 1.0
|
||||||
|
|
||||||
|
# APO settings
|
||||||
|
loss_type: "apo_zero"
|
||||||
|
dpo_beta: 0.5
|
||||||
|
precompute_ref_log_probs: true
|
||||||
|
truncation_mode: "keep_end"
|
||||||
|
|
||||||
|
# Precision and optimization settings
|
||||||
|
torch_compile: false
|
||||||
|
mat_mul_precision: "highest"
|
||||||
|
tf32: true
|
||||||
|
bf16: true
|
||||||
|
gradient_checkpointing: true
|
||||||
|
use_liger_kernel: false
|
||||||
|
static_graph: false
|
||||||
|
|
||||||
|
# Hub settings
|
||||||
|
push_to_hub: false
|
||||||
|
hub_token: null
|
||||||
|
hub_model_id: null
|
||||||
|
|
||||||
|
# Tokenizer and Reference model
|
||||||
|
tokenizer_name_or_path: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Instruct-SFT"
|
||||||
|
chat_template_path: null
|
||||||
|
reference_model: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Instruct-SFT"
|
||||||
|
continual_pretraining: true
|
||||||
|
|
||||||
|
# Checkpoint settings
|
||||||
|
resume_from_checkpoint: null
|
||||||
|
checkpointing_steps: 1000
|
||||||
|
begin_new_stage: true
|
||||||
|
stage_name: "single_cosine"
|
||||||
|
|
||||||
|
# Miscellaneous settings
|
||||||
|
sanity_check: false
|
||||||
|
sanity_check_num_samples: 100000
|
||||||
|
wandb_token: null
|
||||||
|
wandb_id: "tucano2-qwen-1.5b-instruct-apo"
|
||||||
|
wandb_project: "Polyglot"
|
||||||
|
wandb_desc: "Developing LLMs for low-resource languages"
|
||||||
110
training_config_sft.yaml
Normal file
110
training_config_sft.yaml
Normal file
@@ -0,0 +1,110 @@
|
|||||||
|
# Directory settings
|
||||||
|
checkpoint_dir: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Instruct-SFT"
|
||||||
|
train_dataset_dir:
|
||||||
|
# Total: ~874 million tokens (x5 epochs)
|
||||||
|
# Coding: ~2.3 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/code
|
||||||
|
# Function Calling: ~17.5 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/function_call
|
||||||
|
# General Instruction Following: ~700 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/general
|
||||||
|
# Math and CoT: ~27 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/math_cot
|
||||||
|
# Retrieval Augmented Generation: ~2.2 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/retrieval
|
||||||
|
# Structured Outputs: ~35 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/structured
|
||||||
|
# Summarization: ~290 thousand tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/summarization
|
||||||
|
# Translation: ~5.7 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/translation
|
||||||
|
# Chosen Data from Preference Dataset: ~14 million tokens
|
||||||
|
- /polyglot/portuguese/gigaverbo-v2-sft/dpo
|
||||||
|
val_dataset_dir: null
|
||||||
|
dataset_type: "jsonl"
|
||||||
|
cache_dir: "/lustre/mlnvme/data/polyglot/.cache"
|
||||||
|
|
||||||
|
# Data loading settings
|
||||||
|
pin_memory: true
|
||||||
|
num_workers_for_dataloader: 16
|
||||||
|
shuffle_dataset: true
|
||||||
|
mask_eos_token: false
|
||||||
|
mask_pad_token: true
|
||||||
|
|
||||||
|
# Model architecture settings
|
||||||
|
vocab_size: 49152
|
||||||
|
num_hidden_layers: 28
|
||||||
|
num_attention_heads: 16
|
||||||
|
num_key_value_heads: 8
|
||||||
|
head_dim: 128
|
||||||
|
hidden_size: 2048
|
||||||
|
intermediate_size: 6144
|
||||||
|
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: 524288
|
||||||
|
micro_batch_size: 4
|
||||||
|
gradient_accumulation_steps: 4
|
||||||
|
eval_micro_batch_size: null
|
||||||
|
num_train_epochs: 5
|
||||||
|
warmup_ratio: 0.1
|
||||||
|
max_learning_rate: 0.000075
|
||||||
|
min_learning_rate: 0.0
|
||||||
|
muon_learning_rate: null
|
||||||
|
weight_decay: 0.0
|
||||||
|
beta1: 0.9
|
||||||
|
beta2: 0.95
|
||||||
|
eps: 0.00000001
|
||||||
|
lr_decay_type: "cosine"
|
||||||
|
use_sqrt: false
|
||||||
|
lr_decay_iters_coef: 1.
|
||||||
|
seed: 42
|
||||||
|
max_steps: 68635
|
||||||
|
max_grad_norm: 1.0
|
||||||
|
|
||||||
|
# SFT settings
|
||||||
|
packing: false
|
||||||
|
assistant_only_loss: true
|
||||||
|
|
||||||
|
# Precision and optimization settings
|
||||||
|
torch_compile: false
|
||||||
|
mat_mul_precision: "highest"
|
||||||
|
tf32: true
|
||||||
|
bf16: true
|
||||||
|
gradient_checkpointing: true
|
||||||
|
use_liger_kernel: true
|
||||||
|
static_graph: false
|
||||||
|
|
||||||
|
# Hub settings
|
||||||
|
push_to_hub: false
|
||||||
|
hub_token: null
|
||||||
|
hub_model_id: null
|
||||||
|
|
||||||
|
# Tokenizer and Reference model
|
||||||
|
tokenizer_name_or_path: "Polygl0t/Tucano2-qwen-1.5B-Base"
|
||||||
|
chat_template_path: null
|
||||||
|
reference_model: "Polygl0t/Tucano2-qwen-1.5B-Base"
|
||||||
|
continual_pretraining: true
|
||||||
|
|
||||||
|
# Checkpoint settings
|
||||||
|
resume_from_checkpoint: null
|
||||||
|
checkpointing_steps: 1000
|
||||||
|
begin_new_stage: true
|
||||||
|
stage_name: "single_cosine"
|
||||||
|
|
||||||
|
# Miscellaneous settings
|
||||||
|
sanity_check: false
|
||||||
|
sanity_check_num_samples: 100000
|
||||||
|
wandb_token: null
|
||||||
|
wandb_id: "tucano2-qwen-1.5b-instruct-sft"
|
||||||
|
wandb_project: "Polyglot"
|
||||||
|
wandb_desc: "Developing LLMs for low-resource languages"
|
||||||
Reference in New Issue
Block a user