初始化项目，由ModelHub XC社区提供模型
Model: Polygl0t/Tucano2-qwen-1.5B-Think 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
|
||||
.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
|
||||
logo.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 sha256:29bd25077d0963148cb0f4037f0cb8dc118a541def9d889dfefddb3f8aeb09de
|
||||
size 482994
|
||||
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 sha256:3ab2d18bdb9961ad8a8bc0e7274735ebb2c337e2ed2cc389b3b00f81c1e66f7e
|
||||
size 286839
|
||||
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:d798bab25626567c5d6b038d5631782671b04b10684a06daaff40297925e01a8
|
||||
size 217771
|
||||
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 sha256:0de46cb25883cd57d12cb8e6fa41c6e810a209b7ce2e3d797ca5f41831a9f3da
|
||||
size 318225
|
||||
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:c38664279e9165a2b64c2e062894747b34f55953834b96c7613089c0000d39fe
|
||||
size 383372
|
||||
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.
|
||||
531
README.md
Normal file
531
README.md
Normal file
@@ -0,0 +1,531 @@
|
||||
---
|
||||
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: 2550
|
||||
source: CodeCarbon
|
||||
training_type: post-training
|
||||
geographical_location: Germany
|
||||
hardware_used: NVIDIA A100-SXM4-80GB
|
||||
model-index:
|
||||
- name: Tucano2-qwen-1.5B-Think
|
||||
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: 42.82
|
||||
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 (Portuguese)
|
||||
type: Polygl0t/MMLU-poly
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 43.3
|
||||
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 (Portuguese)
|
||||
type: facebook/belebele
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 67.67
|
||||
name: Acc-norm
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: belebele_pot_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: 39.22
|
||||
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: 39.89
|
||||
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: 34.26
|
||||
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_prompt_level_loose_acc
|
||||
value: 33.67
|
||||
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: 22.83
|
||||
name: Acc-flex
|
||||
source:
|
||||
url: https://github.com/Polygl0t/lm-evaluation-harness/tree/polyglot_harness_portuguese
|
||||
name: gsm8k_pt
|
||||
base_model: Polygl0t/Tucano2-qwen-1.5B-Base
|
||||
---
|
||||
|
||||
# Tucano2-qwen-1.5B-Think
|
||||
|
||||
<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-Think](https://huggingface.co/Polygl0t/Tucano2-qwen-1.5B-Think)** is an instruction-tuned Portuguese language model built 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).
|
||||
|
||||
Tucano2-qwen-1.5B-Think is a reasoning model, which means it has been fine-tuned to generate CoT-style (Chain-of-Thought) traces in its responses. These reasoning traces are always encapsulated within the special tokens `<think>` and `</think>`.
|
||||
|
||||
**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**: ~ 1.5 hours
|
||||
- **Emissions:** 2.55 KgCO2 (Germany)
|
||||
- **Total energy consumption:** 5.5 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-Think is to serve as foundations for research and development involving Portuguese language modeling. You may also fine-tune and adapt Tucano2-qwen-1.5B-Think for deployment if your use follows the Apache 2.0 license. If you decide to use Tucano2-qwen-1.5B-Think 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-Think"
|
||||
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
|
||||
full_output = tokenizer.decode(
|
||||
outputs[0][len(inputs.input_ids[0]):],
|
||||
skip_special_tokens=True
|
||||
).strip()
|
||||
|
||||
# Extract <think>...</think> content
|
||||
think_content = None
|
||||
final_response = full_output
|
||||
|
||||
if "<think>" in full_output and "</think>" in full_output:
|
||||
start = full_output.find("<think>") + len("<think>")
|
||||
end = full_output.find("</think>")
|
||||
think_content = full_output[start:end].strip()
|
||||
|
||||
# Remove think block from final response
|
||||
final_response = (
|
||||
full_output[:full_output.find("<think>")] +
|
||||
full_output[end + len("</think>"):]
|
||||
).strip()
|
||||
|
||||
if think_content:
|
||||
print("🧠 Thinking:\n")
|
||||
print(think_content)
|
||||
print("\n" + "="*50 + "\n")
|
||||
|
||||
print("🤖 Answer:\n")
|
||||
print(final_response)
|
||||
```
|
||||
|
||||
## Limitations
|
||||
|
||||
Like almost all other language models trained on large text datasets scraped from the web, the Tucano2-qwen-1.5B-Think 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-Think is subject to the following:
|
||||
|
||||
- **Hallucinations:** Tucano2-qwen-1.5B-Think 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-Think 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-Think 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-Think 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-Think 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 (Think variant) series against other reasoning models of similar size. We divide our evaluations into two sets:
|
||||
|
||||
- **Knowledge & Reasoning:** ARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT
|
||||
- **Instruction Following:** IFEval-PT
|
||||
|
||||
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.
|
||||
|
||||
We do not include coding benchmarks in this table because the Think models were not trained on coding data during post-training and thus perform poorly on them. For coding skills, we recommend using the Instruct models instead, which were trained with coding data and perform much better on coding benchmarks.
|
||||
|
||||
| | Total Avg. | Knowledge & Reasoning (NPM) | Instruction Following |
|
||||
| --------------------------- | ---------- | --------------------------- | --------------------- |
|
||||
| **Tucano2-qwen-3.7B-Think** | 51.27 | 54.07 | 31.67 |
|
||||
| SmolLM3-3B | 48.58 | 46.28 | 64.67 |
|
||||
| Qwen3-4B | 46.35 | 40.97 | 84 |
|
||||
| Qwen3-1.7B | 36.54 | 32 | 68.33 |
|
||||
| **Tucano2-qwen-1.5B-Think** | 27.54 | 26.67 | 33.67 |
|
||||
| Qwen3-0.6B | 24.11 | 19.22 | 58.33 |
|
||||
| **Tucano2-qwen-0.5B-Think** | 14.41 | 12.52 | 27.67 |
|
||||
|
||||
<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` |
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><b>Individual Benchmarks</b></summary>
|
||||
|
||||
| | BLUEX | ENEM | OAB | ARC Challenge | BELEBELE | MMLU | IFEval-PT | GSM8K-PT |
|
||||
| --------------------------- | ----- | ----- | ----- | ------------- | -------- | ----- | --------- | -------- |
|
||||
| **Tucano2-qwen-3.7B-Think** | 63 | 71.52 | 53.76 | 55.38 | 83.56 | 61.18 | 31.67 | 56.7 |
|
||||
| SmolLM3-3B | 48.82 | 60.6 | 42.19 | 52.56 | 77.78 | 52.82 | 64.67 | 72.15 |
|
||||
| Qwen3-4B | 78.3 | 85.23 | 47.97 | 39.66 | 23 | 31.53 | 84 | 77.02 |
|
||||
| Qwen3-1.7B | 68.29 | 72.5 | 39.32 | 35.64 | 22.89 | 22.85 | 68.33 | 71.69 |
|
||||
| **Tucano2-qwen-1.5B-Think** | 39.22 | 39.89 | 34.26 | 42.82 | 67.67 | 43.3 | 33.67 | 22.83 |
|
||||
| Qwen3-0.6B | 43.53 | 48.71 | 34.21 | 29.91 | 22.89 | 22.85 | 58.33 | 58.37 |
|
||||
| **Tucano2-qwen-0.5B-Think** | 34.49 | 31.98 | 27.02 | 32.74 | 36.11 | 36.08 | 27.67 | 14.61 |
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><b>Inference Samples on Various Tasks</b></summary>
|
||||
|
||||
### Cooking
|
||||
|
||||
**Prompt:**
|
||||
|
||||
<|im_start|>user
|
||||
Você pode me dar uma receita simples de Bolo de Brigadeiro?<|im_end|>
|
||||
<|im_start|>assistant
|
||||
|
||||
**Response:**
|
||||
|
||||
<think>
|
||||
O usuário está me pedindo uma receita simplificada de bolo de brigadeiro. Primeiro, vou analisar a solicitação para entender exatamente o que ele precisa. Preciso garantir que a receita seja fácil e rápida de seguir, então decido omitir alguns passos técnicos mais complexos. Agora preciso considerar os ingredientes básicos necessários para fazer um bom bolo de brigadeiro. Vou listar todos eles na minha mente: farinha de trigo, açúcar refinado, ovos grandes, óleo vegetal, leite condensado, chocolate amargo picado e gelatina em pó sem sabor. Devo organizar esses itens numa lista clara e concisa. Além disso, é importante mencionar as etapas principais da preparação do recheio (gelatina dissolvida no leite) e dos dois bolos individuais (farinha peneirada misturada com água morna). Também devo sugerir como untar e enfarinhar formas retangulares pequenas antes de colocar os bolos dentro delas. Finalmente, adicionarei instruções rápidas sobre assar nos forno pré-aquecido e resfriá-los completamente após retirar das formas. Antes de concluir, ofereço ao usuário a opção de pedir dicas extras caso precise. Isso mostra disponibilidade e ajuda quem possa estar buscando informações adicionais.
|
||||
</think>
|
||||
|
||||
Claro! Aqui vai uma versão bem simplificada de **Bolo de Brigadeiro** que você pode preparar rapidamente:
|
||||
|
||||
### Ingredientes:
|
||||
- 2 xícaras de farinha de trigo
|
||||
- 1 xícara de açúcar refinado
|
||||
- 4 ovos grandes
|
||||
- ½ colher de chá de fermento químico incolor
|
||||
- ⅓ copo de óleo vegetal
|
||||
- 3 copos de leite condensado
|
||||
- ₁ lata de chocolate amargo picado (aproximadamente 240g)
|
||||
- Gelatina em pó sem sabor (1 tablete)
|
||||
|
||||
### Modo de Preparo:
|
||||
1. Prepare a forma: Untie e dusted duas formas retangulares pequenos ou use papel manteiga.
|
||||
2. Pré-aqueça o forno a 180°C.
|
||||
3. Em uma panela pequena, derreta metade da gelatina em pó num pouco de água quente. Reserve.
|
||||
4. Misture a outra metade da gelatina não derretida junto com todo o resto da geléia nas formas untadas. Deixe descansar por cerca de 5 minutos até ficar consistente.
|
||||
5. Na batedeira, batam os ovos com o açúcar até obter uma mistura cremosa. Adicione gradualmente a farinha peneirada e mexendo apenas suficiente para combinar.
|
||||
6. Acrescente o fermento químico aos poucos à massa já formada.
|
||||
7. Gradualmente, incorpore o óleo vegetal às massas secas.
|
||||
8. Por último, junte o leite condensado e o chocolate amargo picado. Mexer suavemente só pra misturar tudo uniformemente.
|
||||
9. Preencha cada cavidade das formas preparadas anteriormente com esta mistura.
|
||||
10. Asse durante 25-30 minutos aproximadamente, verificando se estão dourados pelo lado externo usando palitos finos.
|
||||
11. Retire do forno e deixe esfriando totalmente dentro das formas.
|
||||
12. Transfira cuidadosamente para bandejas de gelo cortáveis enquanto ainda estiverem quentes mas manejáveis.
|
||||
13. Sirva fresco logo depois de desconectar do congelador.
|
||||
|
||||
E pronto! Um delicioso Bolinho de Brigadeiros caseiro rapidinho. Espero que goste! Qualquer coisa, estou aqui pra ajudar!<|im_end|>
|
||||
|
||||
---
|
||||
|
||||
### Math
|
||||
|
||||
**Prompt:**
|
||||
|
||||
<|im_start|>user
|
||||
Como eu posso resolver o seguinte problema: 2x + 3 = 11?<|im_end|>
|
||||
<|im_start|>assistant
|
||||
|
||||
**Response:**
|
||||
|
||||
<think>
|
||||
O usuário está me perguntando como resolve-se a equação 2x + 3 = 11. Primeiro, vou analisar cuidadosamente cada elemento da equação. Preciso isolar x no lado esquerdo para descobrir seu valor. Vou começar subtraindo 3 de ambos os lados para eliminar esse termo constante do lado esquerdo. Isso dá duas vezes X igual ao número menos três e onze juntos. Agora tenho que dividir tudo por dois porque quero deixar só X multiplicado pelo coeficiente 2. Deixe-me fazer essa divisão agora. Dividindo 20/2 obtenho 10, então minha solução é x=10. Mas antes de confirmar isso, preciso revisitar todos os passos pra garantir nada foi deixado escapar ou cometido erro algum na manipulação algébrica. Sim, parece correto! Então posso dizer com confiança que a resposta correta é realmente 10.
|
||||
</think>
|
||||
|
||||
Claro! Vamos resolver a equação \( 2x + 3 = 11 \) passo a passo.
|
||||
|
||||
### Passo 1: Isolar o termo com a variável \( x \)
|
||||
Primeiro, vamos remover o termo independente (que não contém \( x \)) do lado onde estamos guardando nossa incógnita. Para isso, subtraímos 3 de ambos os lados da equação:
|
||||
|
||||
\[
|
||||
2x + 3 - 3 = 11 - 3 \\
|
||||
2x = 8
|
||||
\]
|
||||
|
||||
Agora temos apenas \( 2x = 8 \).
|
||||
|
||||
### Passo 2: Resolver para \( x \)
|
||||
Para encontrar o valor de \( x \), precisamos isolá-lo dividindo ambos os lados pela constante que multiplica \( x \):
|
||||
|
||||
\[
|
||||
\frac{2x}{2} = \frac{8}{2}\quad (\text{dividimos ambos os lados por } 2)\\
|
||||
x=4
|
||||
\]
|
||||
|
||||
Portanto, a solução para a equação \( 2x + 3 = 11 \) é \( x = 4 \).
|
||||
|
||||
Se você tiver alguma outra dúvida ou quiser ver outro exemplo, estou aqui para ajudar!<|im_end|>
|
||||
|
||||
---
|
||||
|
||||
### Rewriting
|
||||
|
||||
**Prompt:**
|
||||
|
||||
<|im_start|>user
|
||||
Remova todas as informações irrelevantes da frase a seguir.
|
||||
|
||||
"O novo restaurante que abriu no centro da cidade, de propriedade do primo de Jorge, que costumava ser chef de um restaurante em Ipanema, serve uma variedade de cozinhas de todo o mundo."<|im_end|>
|
||||
<|im_start|>assistant
|
||||
|
||||
**Response:**
|
||||
|
||||
<think>
|
||||
O usuário está me pedindo para remover toda informação desnecessária da frase fornecida. Primeiro, vou ler cuidadosamente a frase completa: 'O novo restaurante que abriu no centro da cidade, de propriedade do primo de Jorge, que costumava ser chefe de um restaurante em Ipanema, serve uma variedade de cozinhas de todo o mundo.' Agora preciso identificar quais partes são realmente importantes e relevantes ao objetivo principal dessa pergunta — entender qual tipo específico de cozinha esse restaurante oferece. Vou começar eliminando detalhes secundários ou redundâncias.
|
||||
</think>
|
||||
|
||||
Entendi! Vamos focar nas informações essenciais sobre o tipo de culinária oferecida pelo restaurante:
|
||||
|
||||
> O novo restaurante no centro da cidade serve uma variedade de cozinhas de todo o mundo.
|
||||
|
||||
Se você quiser alguma outra coisa específica, estou aqui pra ajudar!<|im_end|>
|
||||
|
||||
---
|
||||
|
||||
### History
|
||||
|
||||
**Prompt:**
|
||||
|
||||
<|im_start|>user
|
||||
Liste os principais eventos envolvendo a Revolução Farroupilha.<|im_end|>
|
||||
<|im_start|>assistant
|
||||
|
||||
**Response:**
|
||||
|
||||
<think>
|
||||
O usuário está me perguntando para listar os principais eventos envolvidos na Revolução Farroupilha. Primeiro, vou analisar exatamente o que ele quer saber: são fatos cronológicos importantes e significativos dessa importante revolta gaúcha? Agora preciso lembrar dos detalhes históricos relevantes da época. Vou começar pelo início do movimento, pois isso dá contexto ao leitor sobre quando tudo começou. Devo mencionar as razões iniciais pelas quais surgiu esse conflito entre republicanos farrapos e autoridades imperiais. Depois disso, posso organizar minha lista em ordem temporal, destacando cada evento crucial. Preciso garantir que aborde tanto aspectos políticos quanto sociais-econômicos, já que esses foram elementos cruciais nos motivadores das revoltas locais. Também devo incluir datas aproximadas onde possível para facilitar a compreensão do tempo histórico. Finalmente, concluirei com uma nota geral sobre o impacto duradouro desta revolução no Rio Grande do Sul moderno. Isso ajudará o usuário a ter uma visão completa e contextualizada.
|
||||
</think>
|
||||
|
||||
Claro! A Revolução Farroupilha, também conhecida como Guerra dos Farrapos ou Revolta dos Sargentos, foi um levante militar contra o Império Brasileiro ocorrido nas regiões sulistas atuais de Santa Catarina, Rio Grande do Sul e parte de São Paulo, durante o período imperial (1835-1845). Aqui estão alguns dos principais eventos:
|
||||
|
||||
1. **Início da Rebelião**:
|
||||
- Em março de 1831, eclodiu a primeira insurreição liderada por Bento Gonçalves, ex-soldado desertor do exército regular brasileiro. Inicialmente, esta rebelião visava derrubar o governo centralizado sob dom Pedro I. No entanto, após algumas vitórias militares, ela se transformou numa luta pela autonomia provincial.
|
||||
|
||||
2. **Formação das Províncias Livres**:
|
||||
- Com apoio popular crescente, grupos regionais formaram suas próprias forças armadas independentes chamadas "farrapos". Estas províncias livres incluíram Rio Grande (atual RS), Santa Catarina e Paraná. O líder máximo desses movimentos era Manuel Marques Lisboa, futuro marquês de Alegrete.
|
||||
|
||||
3. **Conflito Militar Principal**:
|
||||
- As hostilidades começaram oficialmente em junho de 1836, marcando o começo formal da guerra civil rio-grandense. Os farrapos enfrentaram tropas imperiais lideradas inicialmente pelos generais David Canabarro e Félix Zavala. Apesar das dificuldades logísticas e numéricas, eles conseguiram manter controle significativo sobre áreas estratégicas.
|
||||
|
||||
4. **Negociação e Trégua Temporária**:
|
||||
- Nos anos seguintes, houve períodos alternados de combates intensos seguidos por acordos negociados visando aliviar tensões temporariamente. Um exemplo notório é a assinatura do Tratado de Ponche Verde em outubro de 1841, embora tenha sido rompido rapidamente depois dele.
|
||||
|
||||
5. **Finalização do Conflito**:
|
||||
- Após várias campanhas bem-sucedidas conduzidas principalmente pelo general José Antônio Correia de Melo, finalmente resultou na queda definitiva de Porto Alegre às mãos imperiais em maio de 1844, encerrando assim efetivamente a maior rebeldia regionalista até então registrada dentro fronteiras brasileiras formais.
|
||||
|
||||
6. **Impacto Político e Social**:
|
||||
- Este conflito teve consequências profundas não só política mas socialmente. Resultou na criação legal da Província do Rio Grande do Sul através Lei Complementar nº 2, assinada logo após término bélico; além disto contribuiu decisivamente formação identidade nacional brasileira questionada muitos intelectuais contemporâneos revolucionários.
|
||||
|
||||
Esses pontos resumem brevemente alguns momentos chave daquela história rica e complexa. Espero que ajude você entender melhor este episódio fascinante da nossa herança cultural!<|im_end|>
|
||||
|
||||
---
|
||||
|
||||
</details>
|
||||
|
||||
Below, we compare the performance of Tucano2-qwen-1.5B-Think 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-Think/tree/main/.plots/) folder.
|
||||
|
||||
**Tucano2-qwen-1.5B-Think 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-Think is licensed under the Apache License, Version 2.0. For more details, see the [LICENSE](LICENSE) file.
|
||||
114
chat_template.jinja
Normal file
114
chat_template.jinja
Normal file
@@ -0,0 +1,114 @@
|
||||
{#- 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 %}
|
||||
|
||||
{#- Detect multi-step tool usage by finding the last real user query #}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{#- 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 with reasoning #}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{#- Extract reasoning content if present #}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{#- Parse <think></think> tags from content #}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{% generation %}
|
||||
{#- Add reasoning tags for messages after last user query #}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- content }}
|
||||
{%- endif %}
|
||||
|
||||
{#- 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: 0.37948717948717947
|
||||
arc_challenge_poly_pt_acc_norm: 0.4282051282051282
|
||||
arc_challenge_poly_pt_acc_norm_stderr: 0.014472341586181985
|
||||
arc_challenge_poly_pt_acc_stderr: 0.014192754090886793
|
||||
arc_challenge_poly_pt_alias: arc_challenge_poly_pt
|
||||
assin2_rte_acc,all: 0.8705065359477124
|
||||
assin2_rte_acc_stderr,all: 0.004798540986291823
|
||||
assin2_rte_alias: assin2_rte
|
||||
assin2_rte_f1_macro,all: 0.8691746625542952
|
||||
assin2_rte_f1_macro_stderr,all: 0.004847278802663799
|
||||
assin2_sts_alias: assin2_sts
|
||||
assin2_sts_mse,all: 2.2781209150326798
|
||||
assin2_sts_mse_stderr,all: N/A
|
||||
assin2_sts_pearson,all: 0.47716809267162485
|
||||
assin2_sts_pearson_stderr,all: 0.014407170423859306
|
||||
assin_entailment_acc: 0.7325
|
||||
assin_entailment_acc_stderr: 0.006999870502142285
|
||||
assin_entailment_alias: assin_entailment
|
||||
assin_paraphrase_acc: 0.73625
|
||||
assin_paraphrase_acc_stderr: 0.006968401827607802
|
||||
assin_paraphrase_alias: assin_paraphrase
|
||||
belebele_por_Latn_acc: 0.6766666666666666
|
||||
belebele_por_Latn_acc_norm: 0.6766666666666666
|
||||
belebele_por_Latn_acc_norm_stderr: 0.015600294087844632
|
||||
belebele_por_Latn_acc_stderr: 0.015600294087844632
|
||||
belebele_por_Latn_alias: belebele_por_Latn
|
||||
bluex_acc,all: 0.39221140472878996
|
||||
bluex_acc,exam_id__UNICAMP_2018: 0.48148148148148145
|
||||
bluex_acc,exam_id__UNICAMP_2019: 0.42
|
||||
bluex_acc,exam_id__UNICAMP_2020: 0.41818181818181815
|
||||
bluex_acc,exam_id__UNICAMP_2021_1: 0.4782608695652174
|
||||
bluex_acc,exam_id__UNICAMP_2021_2: 0.29411764705882354
|
||||
bluex_acc,exam_id__UNICAMP_2022: 0.5384615384615384
|
||||
bluex_acc,exam_id__UNICAMP_2023: 0.4883720930232558
|
||||
bluex_acc,exam_id__UNICAMP_2024: 0.4444444444444444
|
||||
bluex_acc,exam_id__USP_2018: 0.24074074074074073
|
||||
bluex_acc,exam_id__USP_2019: 0.35
|
||||
bluex_acc,exam_id__USP_2020: 0.39285714285714285
|
||||
bluex_acc,exam_id__USP_2021: 0.3076923076923077
|
||||
bluex_acc,exam_id__USP_2022: 0.24489795918367346
|
||||
bluex_acc,exam_id__USP_2023: 0.38636363636363635
|
||||
bluex_acc,exam_id__USP_2024: 0.4634146341463415
|
||||
bluex_acc_stderr,all: 0.010527552369043944
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2018: 0.03932520147192548
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2019: 0.040409592319981036
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2020: 0.038500996629012005
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2021_1: 0.04265317780472471
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2021_2: 0.0369309745845929
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2022: 0.04616267465694302
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2023: 0.04391771882582978
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2024: 0.04266417007528182
|
||||
bluex_acc_stderr,exam_id__USP_2018: 0.03361325629183327
|
||||
bluex_acc_stderr,exam_id__USP_2019: 0.04344929186946837
|
||||
bluex_acc_stderr,exam_id__USP_2020: 0.037457169801895486
|
||||
bluex_acc_stderr,exam_id__USP_2021: 0.03696695228727266
|
||||
bluex_acc_stderr,exam_id__USP_2022: 0.03545185428690165
|
||||
bluex_acc_stderr,exam_id__USP_2023: 0.042474562735645566
|
||||
bluex_acc_stderr,exam_id__USP_2024: 0.04499354148452882
|
||||
bluex_alias: bluex
|
||||
calame_pt_acc: 0.11127167630057803
|
||||
calame_pt_acc_stderr: 0.00690347530269077
|
||||
calame_pt_alias: calame_pt
|
||||
calame_pt_perplexity: 5965.407764074068
|
||||
calame_pt_perplexity_stderr: 683.2371253201818
|
||||
enem_challenge_acc,all: 0.3988803358992302
|
||||
enem_challenge_acc,exam_id__2009: 0.46956521739130436
|
||||
enem_challenge_acc,exam_id__2010: 0.5128205128205128
|
||||
enem_challenge_acc,exam_id__2011: 0.46153846153846156
|
||||
enem_challenge_acc,exam_id__2012: 0.4224137931034483
|
||||
enem_challenge_acc,exam_id__2013: 0.3148148148148148
|
||||
enem_challenge_acc,exam_id__2014: 0.41284403669724773
|
||||
enem_challenge_acc,exam_id__2015: 0.40336134453781514
|
||||
enem_challenge_acc,exam_id__2016: 0.36363636363636365
|
||||
enem_challenge_acc,exam_id__2016_2: 0.4065040650406504
|
||||
enem_challenge_acc,exam_id__2017: 0.39655172413793105
|
||||
enem_challenge_acc,exam_id__2022: 0.3157894736842105
|
||||
enem_challenge_acc,exam_id__2023: 0.32592592592592595
|
||||
enem_challenge_acc_stderr,all: 0.00749197527112301
|
||||
enem_challenge_acc_stderr,exam_id__2009: 0.02676517541031027
|
||||
enem_challenge_acc_stderr,exam_id__2010: 0.02676561702634192
|
||||
enem_challenge_acc_stderr,exam_id__2011: 0.026575632846671127
|
||||
enem_challenge_acc_stderr,exam_id__2012: 0.02652807977680181
|
||||
enem_challenge_acc_stderr,exam_id__2013: 0.02570106484445073
|
||||
enem_challenge_acc_stderr,exam_id__2014: 0.02722456002129014
|
||||
enem_challenge_acc_stderr,exam_id__2015: 0.025882945505526844
|
||||
enem_challenge_acc_stderr,exam_id__2016: 0.025343746567122242
|
||||
enem_challenge_acc_stderr,exam_id__2016_2: 0.025491304109387235
|
||||
enem_challenge_acc_stderr,exam_id__2017: 0.0261642629559971
|
||||
enem_challenge_acc_stderr,exam_id__2022: 0.02331831926729694
|
||||
enem_challenge_acc_stderr,exam_id__2023: 0.023372974631758865
|
||||
enem_challenge_alias: enem
|
||||
faquad_nli_acc,all: 0.7892307692307692
|
||||
faquad_nli_acc_stderr,all: 0.011279066985135663
|
||||
faquad_nli_alias: faquad_nli
|
||||
faquad_nli_f1_macro,all: 0.49256657036543183
|
||||
faquad_nli_f1_macro_stderr,all: 0.01318624622535848
|
||||
global_piqa_completions_por_latn_braz_acc: 0.75
|
||||
global_piqa_completions_por_latn_braz_acc_bytes: 0.74
|
||||
global_piqa_completions_por_latn_braz_acc_bytes_stderr: 0.0440844002276808
|
||||
global_piqa_completions_por_latn_braz_acc_norm: 0.74
|
||||
global_piqa_completions_por_latn_braz_acc_norm_stderr: 0.0440844002276808
|
||||
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: 0.228310502283105
|
||||
gsm8k_pt_exact_match,strict-match: 0.0
|
||||
gsm8k_pt_exact_match_stderr,flexible-extract: 0.011583822031121497
|
||||
gsm8k_pt_exact_match_stderr,strict-match: 0.0
|
||||
hatebr_offensive_acc,all: 0.7071428571428572
|
||||
hatebr_offensive_acc_stderr,all: 0.008611736471385361
|
||||
hatebr_offensive_alias: hatebr_offensive_binary
|
||||
hatebr_offensive_f1_macro,all: 0.7019751844399732
|
||||
hatebr_offensive_f1_macro_stderr,all: 0.008866946580220815
|
||||
hellaswag_poly_pt_acc: 0.4334164048109221
|
||||
hellaswag_poly_pt_acc_norm: 0.5494636471990465
|
||||
hellaswag_poly_pt_acc_norm_stderr: 0.005179413791359488
|
||||
hellaswag_poly_pt_acc_stderr: 0.005158588405358706
|
||||
hellaswag_poly_pt_alias: hellaswag_poly_pt
|
||||
humaneval_instruct_alias: humaneval_instruct
|
||||
humaneval_instruct_pass@1,create_test: 0.0
|
||||
humaneval_instruct_pass@1_stderr,create_test: 0.0
|
||||
ifeval_pt_alias: ifeval_pt
|
||||
ifeval_pt_inst_level_loose_acc: 0.4511627906976744
|
||||
ifeval_pt_inst_level_loose_acc_stderr: N/A
|
||||
ifeval_pt_inst_level_strict_acc: 0.3395348837209302
|
||||
ifeval_pt_inst_level_strict_acc_stderr: N/A
|
||||
ifeval_pt_prompt_level_loose_acc: 0.33666666666666667
|
||||
ifeval_pt_prompt_level_loose_acc_stderr: 0.02732941756218688
|
||||
ifeval_pt_prompt_level_strict_acc: 0.23333333333333334
|
||||
ifeval_pt_prompt_level_strict_acc_stderr: 0.024459979523511425
|
||||
lambada_poly_pt_acc: 0.267028915195032
|
||||
lambada_poly_pt_acc_stderr: 0.00616360274242743
|
||||
lambada_poly_pt_alias: lambada_poly_pt
|
||||
lambada_poly_pt_perplexity: 214.12248648482947
|
||||
lambada_poly_pt_perplexity_stderr: 13.012850955803207
|
||||
mmlu_poly_pt_acc: 0.43297808465926146
|
||||
mmlu_poly_pt_acc_stderr: 0.004292713120965234
|
||||
mmlu_poly_pt_alias: mmlu_poly_pt
|
||||
oab_exams_acc,all: 0.3425968109339408
|
||||
oab_exams_acc,exam_id__2010-01: 0.3176470588235294
|
||||
oab_exams_acc,exam_id__2010-02: 0.33
|
||||
oab_exams_acc,exam_id__2011-03: 0.3333333333333333
|
||||
oab_exams_acc,exam_id__2011-04: 0.3625
|
||||
oab_exams_acc,exam_id__2011-05: 0.325
|
||||
oab_exams_acc,exam_id__2012-06: 0.35
|
||||
oab_exams_acc,exam_id__2012-06a: 0.325
|
||||
oab_exams_acc,exam_id__2012-07: 0.3375
|
||||
oab_exams_acc,exam_id__2012-08: 0.325
|
||||
oab_exams_acc,exam_id__2012-09: 0.24675324675324675
|
||||
oab_exams_acc,exam_id__2013-10: 0.325
|
||||
oab_exams_acc,exam_id__2013-11: 0.2875
|
||||
oab_exams_acc,exam_id__2013-12: 0.3375
|
||||
oab_exams_acc,exam_id__2014-13: 0.3875
|
||||
oab_exams_acc,exam_id__2014-14: 0.325
|
||||
oab_exams_acc,exam_id__2014-15: 0.41025641025641024
|
||||
oab_exams_acc,exam_id__2015-16: 0.3125
|
||||
oab_exams_acc,exam_id__2015-17: 0.3974358974358974
|
||||
oab_exams_acc,exam_id__2015-18: 0.375
|
||||
oab_exams_acc,exam_id__2016-19: 0.41025641025641024
|
||||
oab_exams_acc,exam_id__2016-20: 0.4375
|
||||
oab_exams_acc,exam_id__2016-20a: 0.325
|
||||
oab_exams_acc,exam_id__2016-21: 0.25
|
||||
oab_exams_acc,exam_id__2017-22: 0.375
|
||||
oab_exams_acc,exam_id__2017-23: 0.3125
|
||||
oab_exams_acc,exam_id__2017-24: 0.4
|
||||
oab_exams_acc,exam_id__2018-25: 0.3375
|
||||
oab_exams_acc_stderr,all: 0.005854656489923565
|
||||
oab_exams_acc_stderr,exam_id__2010-01: 0.02913844109530932
|
||||
oab_exams_acc_stderr,exam_id__2010-02: 0.02720413223389449
|
||||
oab_exams_acc_stderr,exam_id__2011-03: 0.02739274623256926
|
||||
oab_exams_acc_stderr,exam_id__2011-04: 0.03103610079124539
|
||||
oab_exams_acc_stderr,exam_id__2011-05: 0.030180181541041882
|
||||
oab_exams_acc_stderr,exam_id__2012-06: 0.030663426761582978
|
||||
oab_exams_acc_stderr,exam_id__2012-06a: 0.03019542051107743
|
||||
oab_exams_acc_stderr,exam_id__2012-07: 0.030587368127940558
|
||||
oab_exams_acc_stderr,exam_id__2012-08: 0.030150394921254077
|
||||
oab_exams_acc_stderr,exam_id__2012-09: 0.028367169852259254
|
||||
oab_exams_acc_stderr,exam_id__2013-10: 0.030312606625205758
|
||||
oab_exams_acc_stderr,exam_id__2013-11: 0.0291233179987808
|
||||
oab_exams_acc_stderr,exam_id__2013-12: 0.030508999749351583
|
||||
oab_exams_acc_stderr,exam_id__2014-13: 0.03131790740981766
|
||||
oab_exams_acc_stderr,exam_id__2014-14: 0.030290399093110758
|
||||
oab_exams_acc_stderr,exam_id__2014-15: 0.032059169494021815
|
||||
oab_exams_acc_stderr,exam_id__2015-16: 0.029833251327948757
|
||||
oab_exams_acc_stderr,exam_id__2015-17: 0.03201117621919014
|
||||
oab_exams_acc_stderr,exam_id__2015-18: 0.0311783808239491
|
||||
oab_exams_acc_stderr,exam_id__2016-19: 0.032162738371024235
|
||||
oab_exams_acc_stderr,exam_id__2016-20: 0.031934266796334064
|
||||
oab_exams_acc_stderr,exam_id__2016-20a: 0.030215012978448332
|
||||
oab_exams_acc_stderr,exam_id__2016-21: 0.027979645441821365
|
||||
oab_exams_acc_stderr,exam_id__2017-22: 0.031096010380049006
|
||||
oab_exams_acc_stderr,exam_id__2017-23: 0.02995046656597778
|
||||
oab_exams_acc_stderr,exam_id__2017-24: 0.03158083933896483
|
||||
oab_exams_acc_stderr,exam_id__2018-25: 0.030481185333792096
|
||||
oab_exams_alias: oab_exams
|
||||
portuguese_hate_speech_acc,all: 0.7097532314923619
|
||||
portuguese_hate_speech_acc_stderr,all: 0.01097429657035187
|
||||
portuguese_hate_speech_alias: portuguese_hate_speech_binary
|
||||
portuguese_hate_speech_f1_macro,all: 0.6922452504317789
|
||||
portuguese_hate_speech_f1_macro_stderr,all: 0.011709050058396507
|
||||
tweetsentbr_acc,all: 0.6422885572139303
|
||||
tweetsentbr_acc_stderr,all: 0.007563312856378464
|
||||
tweetsentbr_alias: tweetsentbr
|
||||
tweetsentbr_f1_macro,all: 0.6428335432993848
|
||||
tweetsentbr_f1_macro_stderr,all: 0.007483756787178434
|
||||
step: 3595
|
||||
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 sha256:444dac3b9e519030276ff7d59d86e392bfb021e6e589f0ebab12e4fff3b25a9b
|
||||
size 3020182248
|
||||
82
ruler.yaml
Normal file
82
ruler.yaml
Normal file
@@ -0,0 +1,82 @@
|
||||
model_name: Tucano2-qwen-1.5B-Think
|
||||
results:
|
||||
niah_pt_multikey_1_1024: 0.706
|
||||
niah_pt_multikey_1_1024_stderr: 0.02039509548493655
|
||||
niah_pt_multikey_1_2048: 0.67
|
||||
niah_pt_multikey_1_2048_stderr: 0.021049612166134782
|
||||
niah_pt_multikey_1_4096: 0.542
|
||||
niah_pt_multikey_1_4096_stderr: N/A
|
||||
niah_pt_multikey_1_alias: " - niah_pt_multikey_1"
|
||||
niah_pt_multikey_2_1024: 0.48
|
||||
niah_pt_multikey_2_1024_stderr: 0.022365160424231326
|
||||
niah_pt_multikey_2_2048: 0.238
|
||||
niah_pt_multikey_2_2048_stderr: 0.019064072958198387
|
||||
niah_pt_multikey_2_4096: 0.062
|
||||
niah_pt_multikey_2_4096_stderr: N/A
|
||||
niah_pt_multikey_2_alias: " - niah_pt_multikey_2"
|
||||
niah_pt_multikey_3_1024: 0.486
|
||||
niah_pt_multikey_3_1024_stderr: 0.022374298166353144
|
||||
niah_pt_multikey_3_2048: 0.31
|
||||
niah_pt_multikey_3_2048_stderr: 0.020704041021724684
|
||||
niah_pt_multikey_3_4096: 0.184
|
||||
niah_pt_multikey_3_4096_stderr: N/A
|
||||
niah_pt_multikey_3_alias: " - niah_pt_multikey_3"
|
||||
niah_pt_multiquery_1024: 0.531
|
||||
niah_pt_multiquery_1024_stderr: 0.013691344193015646
|
||||
niah_pt_multiquery_2048: 0.4915
|
||||
niah_pt_multiquery_2048_stderr: 0.014053487147395266
|
||||
niah_pt_multiquery_4096: 0.4215
|
||||
niah_pt_multiquery_4096_stderr: N/A
|
||||
niah_pt_multiquery_alias: " - niah_pt_multiquery"
|
||||
niah_pt_multivalue_1024: 0.4995
|
||||
niah_pt_multivalue_1024_stderr: 0.013476376569794338
|
||||
niah_pt_multivalue_2048: 0.519
|
||||
niah_pt_multivalue_2048_stderr: 0.013327913059930505
|
||||
niah_pt_multivalue_4096: 0.4545
|
||||
niah_pt_multivalue_4096_stderr: N/A
|
||||
niah_pt_multivalue_alias: " - niah_pt_multivalue"
|
||||
niah_pt_single_1_1024: 0.82
|
||||
niah_pt_single_1_1024_stderr: 0.017198592476314233
|
||||
niah_pt_single_1_2048: 0.816
|
||||
niah_pt_single_1_2048_stderr: 0.017346174781752842
|
||||
niah_pt_single_1_4096: 0.8
|
||||
niah_pt_single_1_4096_stderr: N/A
|
||||
niah_pt_single_1_alias: " - niah_pt_single_1"
|
||||
niah_pt_single_2_1024: 0.778
|
||||
niah_pt_single_2_1024_stderr: 0.018604414758250098
|
||||
niah_pt_single_2_2048: 0.772
|
||||
niah_pt_single_2_2048_stderr: 0.018781306529363172
|
||||
niah_pt_single_2_4096: 0.688
|
||||
niah_pt_single_2_4096_stderr: N/A
|
||||
niah_pt_single_2_alias: " - niah_pt_single_2"
|
||||
niah_pt_single_3_1024: 0.468
|
||||
niah_pt_single_3_1024_stderr: 0.022337186479044296
|
||||
niah_pt_single_3_2048: 0.508
|
||||
niah_pt_single_3_2048_stderr: 0.022380208834928014
|
||||
niah_pt_single_3_4096: 0.5
|
||||
niah_pt_single_3_4096_stderr: N/A
|
||||
niah_pt_single_3_alias: " - niah_pt_single_3"
|
||||
ruler_pt_4096: 0.44008484848484847
|
||||
ruler_pt_4096_stderr: N/A
|
||||
ruler_pt_alias: ruler_pt
|
||||
ruler_pt_cwe_1024: 0.2516
|
||||
ruler_pt_cwe_1024_stderr: 0.0065879953982022075
|
||||
ruler_pt_cwe_2048: 0.10560000000000001
|
||||
ruler_pt_cwe_2048_stderr: 0.0046626989526502875
|
||||
ruler_pt_cwe_4096: 0.268
|
||||
ruler_pt_cwe_4096_stderr: N/A
|
||||
ruler_pt_cwe_alias: " - ruler_pt_cwe"
|
||||
ruler_pt_fwe_1024: 0.7766666666666666
|
||||
ruler_pt_fwe_1024_stderr: 0.010771818051204566
|
||||
ruler_pt_fwe_2048: 0.644
|
||||
ruler_pt_fwe_2048_stderr: 0.010544896116732008
|
||||
ruler_pt_fwe_4096: 0.5413333333333332
|
||||
ruler_pt_fwe_4096_stderr: N/A
|
||||
ruler_pt_fwe_alias: " - ruler_pt_fwe"
|
||||
ruler_pt_vt_1024: 0.8336
|
||||
ruler_pt_vt_1024_stderr: 0.01194434656352784
|
||||
ruler_pt_vt_2048: 0.4344
|
||||
ruler_pt_vt_2048_stderr: 0.014185758756689964
|
||||
ruler_pt_vt_4096: 0.37960000000000005
|
||||
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 sha256:17955b2e6b87674c99c03a62da0015c4109d0bdb29dff4c0ed0d7c72897ba58e
|
||||
size 46633
|
||||
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:e96a3c5634dcc1082cefe019f9e271da5e9ca6a9c7cf02823d48f18f8f44baa7
|
||||
size 66628
|
||||
98
training_config_apo.yaml
Normal file
98
training_config_apo.yaml
Normal file
@@ -0,0 +1,98 @@
|
||||
# Directory settings
|
||||
checkpoint_dir: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Think"
|
||||
train_dataset_dir:
|
||||
# Total: 13,649 samples (x5 epochs)
|
||||
# Harmfull samples (with reasoning): 4,008 samples
|
||||
- /polyglot/portuguese/gigaverbo-v2-dpo/harmfull-reasoning
|
||||
# Harmless samples (with reasoning): 9,641 samples
|
||||
- /polyglot/portuguese/gigaverbo-v2-dpo/harmless-reasoning
|
||||
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: 535
|
||||
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-Think-SFT"
|
||||
chat_template_path: null
|
||||
reference_model: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Think-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-think-apo"
|
||||
wandb_project: "Polyglot"
|
||||
wandb_desc: "Developing LLMs for low-resource languages"
|
||||
93
training_config_sft.yaml
Normal file
93
training_config_sft.yaml
Normal file
@@ -0,0 +1,93 @@
|
||||
# Directory settings
|
||||
checkpoint_dir: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Think-SFT"
|
||||
train_dataset_dir:
|
||||
# Reasoning: ~34 million tokens (x5 epochs)
|
||||
- /polyglot/portuguese/gigaverbo-v2-sft/reasoning
|
||||
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: 3060
|
||||
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-think-sft"
|
||||
wandb_project: "Polyglot"
|
||||
wandb_desc: "Developing LLMs for low-resource languages"
|
||||
Reference in New Issue
Block a user