初始化项目，由ModelHub XC社区提供模型
Model: nicholasKluge/TeenyTinyLlama-460m Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
*.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
|
||||||
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
|
||||||
|
|
||||||
|
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.
|
||||||
382
README.md
Normal file
382
README.md
Normal file
@@ -0,0 +1,382 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- pt
|
||||||
|
license: apache-2.0
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
datasets:
|
||||||
|
- nicholasKluge/Pt-Corpus-Instruct
|
||||||
|
metrics:
|
||||||
|
- perplexity
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
widget:
|
||||||
|
- text: 'A PUCRS é uma universidade '
|
||||||
|
example_title: Exemplo
|
||||||
|
- text: A muitos anos atrás, em uma galáxia muito distante, vivia uma raça de
|
||||||
|
example_title: Exemplo
|
||||||
|
- text: Em meio a um escândalo, a frente parlamentar pediu ao Senador Silva para
|
||||||
|
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: 41100
|
||||||
|
source: CodeCarbon
|
||||||
|
training_type: pre-training
|
||||||
|
geographical_location: Germany
|
||||||
|
hardware_used: NVIDIA A100-SXM4-40GB
|
||||||
|
model-index:
|
||||||
|
- name: TeenyTinyLlama-460m
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: ENEM Challenge (No Images)
|
||||||
|
type: eduagarcia/enem_challenge
|
||||||
|
split: train
|
||||||
|
args:
|
||||||
|
num_few_shot: 3
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 20.15
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: BLUEX (No Images)
|
||||||
|
type: eduagarcia-temp/BLUEX_without_images
|
||||||
|
split: train
|
||||||
|
args:
|
||||||
|
num_few_shot: 3
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 25.73
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- 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: 27.02
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: Assin2 RTE
|
||||||
|
type: assin2
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 15
|
||||||
|
metrics:
|
||||||
|
- type: f1_macro
|
||||||
|
value: 53.61
|
||||||
|
name: f1-macro
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: Assin2 STS
|
||||||
|
type: eduagarcia/portuguese_benchmark
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 15
|
||||||
|
metrics:
|
||||||
|
- type: pearson
|
||||||
|
value: 13.0
|
||||||
|
name: pearson
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: FaQuAD NLI
|
||||||
|
type: ruanchaves/faquad-nli
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 15
|
||||||
|
metrics:
|
||||||
|
- type: f1_macro
|
||||||
|
value: 46.41
|
||||||
|
name: f1-macro
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: HateBR Binary
|
||||||
|
type: ruanchaves/hatebr
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 25
|
||||||
|
metrics:
|
||||||
|
- type: f1_macro
|
||||||
|
value: 33.59
|
||||||
|
name: f1-macro
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: PT Hate Speech Binary
|
||||||
|
type: hate_speech_portuguese
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 25
|
||||||
|
metrics:
|
||||||
|
- type: f1_macro
|
||||||
|
value: 22.99
|
||||||
|
name: f1-macro
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: tweetSentBR
|
||||||
|
type: eduagarcia-temp/tweetsentbr
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 25
|
||||||
|
metrics:
|
||||||
|
- type: f1_macro
|
||||||
|
value: 17.28
|
||||||
|
name: f1-macro
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m
|
||||||
|
name: Open Portuguese LLM Leaderboard
|
||||||
|
---
|
||||||
|
# TeenyTinyLlama-460m
|
||||||
|
|
||||||
|
<img src="./logo.png" alt="A curious llama exploring a mushroom forest." height="200">
|
||||||
|
|
||||||
|
## Model Summary
|
||||||
|
|
||||||
|
Large language models (LLMs) have significantly advanced natural language processing, but their progress has yet to be equal across languages. While most LLMs are trained in high-resource languages like English, multilingual models generally underperform monolingual ones. Additionally, aspects of their multilingual foundation sometimes restrict the byproducts they produce, like computational demands and licensing regimes. Hence, we developed the _TeenyTinyLlama_ pair: two compact models for Brazilian Portuguese text generation.
|
||||||
|
|
||||||
|
Read our article [here](https://www.sciencedirect.com/science/article/pii/S2666827024000343).
|
||||||
|
|
||||||
|
## Details
|
||||||
|
|
||||||
|
- **Architecture:** a Transformer-based model pre-trained via causal language modeling
|
||||||
|
- **Size:** 468,239,360 parameters
|
||||||
|
- **Context length:** 2048 tokens
|
||||||
|
- **Dataset:** [Pt-Corpus Instruct](https://huggingface.co/datasets/nicholasKluge/Pt-Corpus-Instruct) (6.2B tokens)
|
||||||
|
- **Language:** Portuguese
|
||||||
|
- **Number of steps:** 1,200,000
|
||||||
|
- **GPU:** 1 NVIDIA A100-SXM4-40GB
|
||||||
|
- **Training time**: ~ 280 hours
|
||||||
|
- **Emissions:** 41.1 KgCO2 (Germany)
|
||||||
|
- **Total energy consumption:** 115.69 kWh
|
||||||
|
|
||||||
|
This repository has the [source code](https://github.com/Nkluge-correa/TeenyTinyLlama) used to train this model. The main libraries used are:
|
||||||
|
|
||||||
|
- [Transformers](https://github.com/huggingface/transformers)
|
||||||
|
- [PyTorch](https://github.com/pytorch/pytorch)
|
||||||
|
- [Datasets](https://github.com/huggingface/datasets)
|
||||||
|
- [Tokenizers](https://github.com/huggingface/tokenizers)
|
||||||
|
- [Sentencepiece](https://github.com/google/sentencepiece)
|
||||||
|
- [Accelerate](https://github.com/huggingface/accelerate)
|
||||||
|
- [FlashAttention](https://github.com/Dao-AILab/flash-attention)
|
||||||
|
- [Codecarbon](https://github.com/mlco2/codecarbon)
|
||||||
|
|
||||||
|
## Intended Uses
|
||||||
|
|
||||||
|
The primary intended use of TeenyTinyLlama is to research the challenges related to developing language models for low-resource languages. Checkpoints saved during training are intended to provide a controlled setting for performing scientific experiments. You may also further fine-tune and adapt TeenyTinyLlama for deployment, as long as your use is following the Apache 2.0 license. If you decide to use pre-trained TeenyTinyLlama as a basis for your fine-tuned model, please conduct your own risk and bias assessment.
|
||||||
|
|
||||||
|
## Out-of-scope Use
|
||||||
|
|
||||||
|
TeenyTinyLlama is not intended for deployment. It is not a product and should not be used for human-facing interactions.
|
||||||
|
|
||||||
|
TeenyTinyLlama models are Brazilian Portuguese language only and are not suitable for translation or generating text in other languages.
|
||||||
|
|
||||||
|
TeenyTinyLlama has not been fine-tuned for downstream contexts in which language models are commonly deployed.
|
||||||
|
|
||||||
|
## Basic usage
|
||||||
|
|
||||||
|
Using the `pipeline`:
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import pipeline
|
||||||
|
|
||||||
|
generator = pipeline("text-generation", model="nicholasKluge/TeenyTinyLlama-460m")
|
||||||
|
|
||||||
|
completions = generator("Astronomia é a ciência", num_return_sequences=2, max_new_tokens=100)
|
||||||
|
|
||||||
|
for comp in completions:
|
||||||
|
print(f"🤖 {comp['generated_text']}")
|
||||||
|
```
|
||||||
|
|
||||||
|
Using the `AutoTokenizer` and `AutoModelForCausalLM`:
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
import torch
|
||||||
|
|
||||||
|
# Load model and the tokenizer
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("nicholasKluge/TeenyTinyLlama-460m", revision='main')
|
||||||
|
model = AutoModelForCausalLM.from_pretrained("nicholasKluge/TeenyTinyLlama-460m", revision='main')
|
||||||
|
|
||||||
|
# Pass the model to your device
|
||||||
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||||
|
|
||||||
|
model.eval()
|
||||||
|
model.to(device)
|
||||||
|
|
||||||
|
# Tokenize the inputs and pass them to the device
|
||||||
|
inputs = tokenizer("Astronomia é a ciência", return_tensors="pt").to(device)
|
||||||
|
|
||||||
|
# Generate some text
|
||||||
|
completions = model.generate(**inputs, num_return_sequences=2, max_new_tokens=100)
|
||||||
|
|
||||||
|
# Print the generated text
|
||||||
|
for i, completion in enumerate(completions):
|
||||||
|
print(f'🤖 {tokenizer.decode(completion)}')
|
||||||
|
```
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
Like almost all other language models trained on large text datasets scraped from the web, the TTL pair exhibited behavior that does not make them an out-of-the-box solution to many real-world applications, especially those requiring factual, reliable, nontoxic text generation. Our models are all subject to the following:
|
||||||
|
|
||||||
|
- **Hallucinations:** This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.
|
||||||
|
|
||||||
|
- **Biases and Toxicity:** This model 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.
|
||||||
|
|
||||||
|
- **Unreliable Code:** The model may produce incorrect code snippets and statements. These code generations should not be treated as suggestions or accurate solutions.
|
||||||
|
|
||||||
|
- **Language Limitations:** The model is primarily designed to understand standard Brazilian Portuguese. Other languages might challenge its comprehension, leading to potential misinterpretations or errors in response.
|
||||||
|
|
||||||
|
- **Repetition and Verbosity:** The model 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 our models are released with a permissive license, we urge users to perform their risk analysis on these models if intending to use them for real-world applications and also have humans moderating the outputs of these models in applications where they will interact with an audience, guaranteeing users are always aware they are interacting with a language model.
|
||||||
|
|
||||||
|
## Evaluations
|
||||||
|
|
||||||
|
During our training runs, both models showed consistent convergence. At no point did our evaluation curves show signs of overfitting or saturation. In the case of our 460m parameter model, we intentionally trained past the optimal point by approximately 75,000 steps to assess if there were any signs of saturation, but our evaluations consistently gave better results. We hypothesize that our models are under-trained but can improve if further trained to pass the Chinchilla optimal range.
|
||||||
|
|
||||||
|
| Processed Tokens | Perplexity | Energy Consumption (kWh) | Emissions (KgCO2eq) |
|
||||||
|
|------------------|------------|---------------------------|----------------------|
|
||||||
|
| 8.1M | 20.49 | 9.40 | 3.34 |
|
||||||
|
| 1.6B | 16.90 | 18.82 | 6.70 |
|
||||||
|
| 2.4B | 15.43 | 28.59 | 10.16 |
|
||||||
|
| 3.2B | 14.64 | 38.20 | 13.57 |
|
||||||
|
| 4.0B | 14.08 | 48.04 | 17.07 |
|
||||||
|
| 4.9B | 13.61 | 57.74 | 20.52 |
|
||||||
|
| 5.7B | 13.25 | 67.32 | 23.92 |
|
||||||
|
| 6.5B | 12.87 | 76.84 | 27.30 |
|
||||||
|
| 7.3B | 12.57 | 86.40 | 30.70 |
|
||||||
|
| 8.1B | 12.27 | 96.19 | 34.18 |
|
||||||
|
| 9.0B | 11.96 | 106.06 | 37.70 |
|
||||||
|
| 9.8B | 11.77 | 115.69 | 41.31 |
|
||||||
|
|
||||||
|
## Benchmarks
|
||||||
|
|
||||||
|
Evaluations on benchmarks were performed using the [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) (by [EleutherAI](https://www.eleuther.ai/)). [Laiviet](https://github.com/laiviet/lm-evaluation-harness) translated the tasks from the LM-Evaluation-Harness we used. The results of models marked with an "*" were extracted from the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
|
||||||
|
|
||||||
|
| | **ARC** | **HellaSwag** | **MMLU** | **TruthfulQA** | **Average** |
|
||||||
|
|------------------|-----------|---------------|-----------|----------------|-------------|
|
||||||
|
| Pythia-410m | 24.83* | 41.29* | 25.99* | 40.95* | 33.26 |
|
||||||
|
| **TTL-460m** | 29.40 | 33.00 | 28.55 | 41.10 | 33.01 |
|
||||||
|
| Bloom-560m | 24.74* | 37.15* | 24.22* | 42.44* | 32.13 |
|
||||||
|
| Xglm-564M | 25.56 | 34.64* | 25.18* | 42.53 | 31.97 |
|
||||||
|
| OPT-350m | 23.55* | 36.73* | 26.02* | 40.83* | 31.78 |
|
||||||
|
| **TTL-160m** | 26.15 | 29.29 | 28.11 | 41.12 | 31.16 |
|
||||||
|
| Pythia-160m | 24.06* | 31.39* | 24.86* | 44.34* | 31.16 |
|
||||||
|
| OPT-125m | 22.87* | 31.47* | 26.02* | 42.87* | 30.80 |
|
||||||
|
| GPorTuguese-2 | 22.48 | 29.62 | 27.36 | 41.44 | 30.22 |
|
||||||
|
| Gpt2-small | 21.48* | 31.60* | 25.79* | 40.65* | 29.97 |
|
||||||
|
| Multilingual GPT | 23.81 | 26.37* | 25.17* | 39.62 | 28.73 |
|
||||||
|
|
||||||
|
Evaluations on Brazilian Portuguese benchmarks were performed using a [Portuguese implementation of the EleutherAI LM Evaluation Harness](https://github.com/eduagarcia/lm-evaluation-harness-pt) (created by [Eduardo Garcia](https://github.com/eduagarcia/lm-evaluation-harness-pt)).
|
||||||
|
|
||||||
|
| | **ASSIN2 RTE** | **ASSIN2 STS** | **BLUEX** | **ENEM** | **FAQUAD NLI** | **HateBR** | **OAB Exams** | **Average** |
|
||||||
|
|----------------|----------------|----------------|-----------|----------|----------------|------------|---------------|-------------|
|
||||||
|
| Qwen-1.8B | 64.83 | 19.53 | 26.15 | 30.23 | 43.97 | 33.33 | 27.20 | 35.03 |
|
||||||
|
| TinyLlama-1.1B | 58.93 | 13.57 | 22.81 | 22.25 | 43.97 | 36.92 | 23.64 | 31.72 |
|
||||||
|
| **TTL-460m** | 53.93 | 12.66 | 22.81 | 19.87 | 49.01 | 33.59 | 27.06 | 31.27 |
|
||||||
|
| XGLM-564m | 49.61 | 22.91 | 19.61 | 19.38 | 43.97 | 33.99 | 23.42 | 30.41 |
|
||||||
|
| Bloom-1b7 | 53.60 | 4.81 | 21.42 | 18.96 | 43.97 | 34.89 | 23.05 | 28.67 |
|
||||||
|
| **TTL-160m** | 53.36 | 2.58 | 21.84 | 18.75 | 43.97 | 36.88 | 22.60 | 28.56 |
|
||||||
|
| OPT-125m | 39.77 | 2.00 | 21.84 | 17.42 | 43.97 | 47.04 | 22.78 | 27.83 |
|
||||||
|
| Pythia-160 | 33.33 | 12.81 | 16.13 | 16.66 | 50.36 | 41.09 | 22.82 | 27.60 |
|
||||||
|
| OLMo-1b | 34.12 | 9.28 | 18.92 | 20.29 | 43.97 | 41.33 | 22.96 | 27.26 |
|
||||||
|
| Bloom-560m | 33.33 | 8.48 | 18.92 | 19.03 | 43.97 | 37.07 | 23.05 | 26.26 |
|
||||||
|
| Pythia-410m | 33.33 | 4.80 | 19.47 | 19.45 | 43.97 | 33.33 | 23.01 | 25.33 |
|
||||||
|
| OPT-350m | 33.33 | 3.65 | 20.72 | 17.35 | 44.71 | 33.33 | 23.01 | 25.15 |
|
||||||
|
| GPT-2 small | 33.26 | 0.00 | 10.43 | 11.20 | 43.52 | 33.68 | 13.12 | 20.74 |
|
||||||
|
| GPorTuguese | 33.33 | 3.85 | 14.74 | 3.01 | 28.81 | 33.33 | 21.23 | 19.75 |
|
||||||
|
| Samba-1.1B | 33.33 | 1.30 | 8.07 | 10.22 | 17.72 | 35.79 | 15.03 | 17.35 |
|
||||||
|
|
||||||
|
## Fine-Tuning Comparisons
|
||||||
|
|
||||||
|
To further evaluate the downstream capabilities of our models, we decided to employ a basic fine-tuning procedure for our TTL pair on a subset of tasks from the Poeta benchmark. We apply the same procedure for comparison purposes on both [BERTimbau](https://huggingface.co/neuralmind/bert-base-portuguese-cased) models, given that they are also LLM trained from scratch in Brazilian Portuguese and have a similar size range to our models. We used these comparisons to assess if our pre-training runs produced LLM capable of producing good results ("good" here means "close to BERTimbau") when utilized for downstream applications.
|
||||||
|
|
||||||
|
| Models | IMDB | FaQuAD-NLI | HateBr | Assin2 | AgNews | Average |
|
||||||
|
|-----------------|-----------|------------|-----------|-----------|-----------|---------|
|
||||||
|
| BERTimbau-large | **93.58** | 92.26 | 91.57 | **88.97** | 94.11 | 92.10 |
|
||||||
|
| BERTimbau-small | 92.22 | **93.07** | 91.28 | 87.45 | 94.19 | 91.64 |
|
||||||
|
| **TTL-460m** | 91.64 | 91.18 | **92.28** | 86.43 | **94.42** | 91.19 |
|
||||||
|
| **TTL-160m** | 91.14 | 90.00 | 90.71 | 85.78 | 94.05 | 90.34 |
|
||||||
|
|
||||||
|
All the shown results are the higher accuracy scores achieved on the respective task test sets after fine-tuning the models on the training sets. All fine-tuning runs used the same hyperparameters, and the code implementation can be found in the [model cards](https://huggingface.co/nicholasKluge/TeenyTinyLlama-460m-HateBR) of our fine-tuned models.
|
||||||
|
|
||||||
|
## Cite as 🤗
|
||||||
|
|
||||||
|
```latex
|
||||||
|
@misc{correa24ttllama,
|
||||||
|
title = {TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese},
|
||||||
|
author = {Corr{\^e}a, Nicholas Kluge and Falk, Sophia and Fatimah, Shiza and Sen, Aniket and De Oliveira, Nythamar},
|
||||||
|
journal={arXiv preprint arXiv:2401.16640},
|
||||||
|
year={2024}
|
||||||
|
}
|
||||||
|
|
||||||
|
@misc{correa24ttllama,
|
||||||
|
doi = {10.1016/j.mlwa.2024.100558},
|
||||||
|
url = {https://www.sciencedirect.com/science/article/pii/S2666827024000343},
|
||||||
|
title = {TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese},
|
||||||
|
author = {Corr{\^e}a, Nicholas Kluge and Falk, Sophia and Fatimah, Shiza and Sen, Aniket and De Oliveira, Nythamar},
|
||||||
|
journal={Machine Learning With Applications},
|
||||||
|
publisher = {Springer},
|
||||||
|
year={2024}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
## Funding
|
||||||
|
|
||||||
|
This repository was built as part of the RAIES ([Rede de Inteligência Artificial Ética e Segura](https://www.raies.org/)) initiative, a project supported by FAPERGS - ([Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul](https://fapergs.rs.gov.br/inicial)), Brazil.
|
||||||
|
|
||||||
|
## License
|
||||||
|
|
||||||
|
TeenyTinyLlama-460m is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
||||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "nicholasKluge/TeenyTinyLlama-460m",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1024,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 4096,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 24,
|
||||||
|
"num_key_value_heads": 16,
|
||||||
|
"pad_token_id": 3,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.35.2",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
2
emissions.csv
Normal file
2
emissions.csv
Normal file
@@ -0,0 +1,2 @@
|
|||||||
|
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
||||||
|
2024-01-03T13:51:28,TeenyTinyLlama,45715238-8bce-4728-96e2-1f71f14ba5d4,1009909.606500864,41.28941942540837,4.007573750865538e-05,42.5,47.67656521740482,31.303916931152344,11.922522712083655,92.27103601704754,8.78049825778793,112.97405698691946,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
19
emissions_training_log.csv
Normal file
19
emissions_training_log.csv
Normal file
@@ -0,0 +1,19 @@
|
|||||||
|
step,timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
||||||
|
100000,2024-01-03T13:51:28,TeenyTinyLlama,45715238-8bce-4728-96e2-1f71f14ba5d4,83440.19941878319,3.343927529577014,4.007573750865538e-05,42.5,56.200428618622695,31.303916931152344,0.985056081838576,7.439017379820253,0.7254148223563788,9.149488284015176,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
175000,2024-01-04T12:15:00,TeenyTinyLlama,221c5b9e-e20a-44b3-9fa1-83e74779aaae,64999.39519429207,2.5819413566384317,3.9722544323999574e-05,42.5,53.26317929955615,31.303916931152344,0.7673525550117105,5.731973730853094,0.5652533091259107,7.064579594990743,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
200000,2024-01-04T20:29:41,TeenyTinyLlama,0ea264bf-c7c9-460b-b625-6c3b31926fdd,23522.980600118637,0.9541841041933724,4.05639115388532e-05,42.5,57.260100405500665,31.303916931152344,0.2777013568489082,2.128589000647616,0.20450075711088017,2.61079111460741,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
225000,2024-01-04T19:48:47,TeenyTinyLlama,0ea264bf-c7c9-460b-b625-6c3b31926fdd,21068.72519850731,0.8560849248279312,4.063297217852477e-05,42.5,57.714695994800806,31.303916931152344,0.2487275589793915,1.910483655607924,0.1831658018266572,2.342377016413977,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
250000,2024-01-05T02:28:48,TeenyTinyLlama,dfc6bc14-e95c-465b-a31d-d7ba966fcd75,20913.65769481659,0.8575542175981553,4.1004506725320384e-05,42.5,0.0,31.303916931152344,0.2468968947321176,1.9175267509646177,0.1819735765584382,2.346397222255177,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
275000,2024-01-05T20:03:05,TeenyTinyLlama,0c0469c9-0346-49c4-81c4-d0b2d21b30f6,20985.887166261673,0.8851270656142388,4.2177252674703636e-05,42.5,54.835770424688086,31.303916931152344,0.24774961942235602,1.991643052479834,0.18244800648315063,2.42184067838534,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
300000,2024-01-05T20:03:05,TeenyTinyLlama,0c0469c9-0346-49c4-81c4-d0b2d21b30f6,20985.88716626168,0.8851270656142388,4.217725267470364e-05,42.5,54.835770424688086,31.303916931152344,0.247749619422356,1.991643052479834,0.1824480064831506,2.42184067838534,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
325000,2024-01-05T20:03:05,TeenyTinyLlama,0c0469c9-0346-49c4-81c4-d0b2d21b30f6,20985.88716626168,0.8851270656142388,4.217725267470364e-05,42.5,54.835770424688086,31.303916931152344,0.247749619422356,1.991643052479834,0.1824480064831506,2.42184067838534,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
375000,2024-01-06T01:51:45,TeenyTinyLlama,0c0469c9-0346-49c4-81c4-d0b2d21b30f6,41905.98246955872,1.7694355720975723,4.222393719996717e-05,42.5,55.734935386481176,31.303916931152344,0.4947225365597342,3.9823935611900776,0.36432555821643,4.841441655966237,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
450000,2024-01-07T08:32:38,TeenyTinyLlama,d4ccf79e-a87d-4bca-baa4-11f0bef1b4ab,62846.51844596863,2.4880971186580183,3.959005494945791e-05,42.5,47.717072999847296,31.303916931152344,0.7419367082600794,5.5194911469782735,0.5463798006688901,6.807807655907262,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
550000,2024-01-08T14:18:45,TeenyTinyLlama,bb223024-b329-4115-8380-c67f6af71a60,83615.6481924057,3.4165899086516185,4.0860652073040155e-05,42.5,53.11319747513939,31.303916931152344,0.9871274375443637,7.63424795878237,0.7269280773572344,9.34830347368403,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
650000,2024-01-09T16:20:36,TeenyTinyLlama,b534a05f-3070-4d29-a742-9306e8287d6a,83853.06784415245,3.481276835668245,4.1516392007725624e-05,42.5,55.84163773271414,31.303916931152344,0.9899303546582688,7.806367793144794,0.7289984800783825,9.525296627881495,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
750000,2024-01-10T16:41:46,TeenyTinyLlama,7732e029-31ab-4496-8702-2cb36db55a63,83781.28784894943,3.3421822192044814,3.989175035397108e-05,42.5,49.71943959971725,31.303916931152344,0.9890829394540829,7.427252594297323,0.7283773187795345,9.144712852531026,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
850000,2024-01-11T16:31:08,TeenyTinyLlama,e7eb95ed-259f-4b2c-a47e-9d7ee2b62b1a,84026.71119689941,3.4252188672721866,4.076345269834358e-05,42.5,50.254842093187335,31.303916931152344,0.9919801959185077,7.6494270778701,0.7305063275383444,9.371913601326996,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
950000,2024-01-12T17:02:17,TeenyTinyLlama,67c822c4-cf62-4462-ba3d-be09831cc33e,83703.14569234848,3.3783003485574086,4.036049446665214e-05,42.5,50.786469757999896,31.303916931152344,0.9881604257664772,7.5276911860370195,0.7276858708763908,9.243537482679919,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
1050000,2024-01-13T16:49:08,TeenyTinyLlama,9faece59-ef8d-4b94-b758-3adf2c2bbf8f,83707.1171541214,3.5784480074210285,4.274962666355355e-05,42.5,0.0,31.303916931152344,0.9882071583160092,8.074966741079336,0.7279976583799046,9.79117155777526,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
1150000,2024-01-14T23:50:40,TeenyTinyLlama,f9fd7bee-55eb-40ba-9251-32cb14c6f8c7,83776.25400185585,3.462136933877389,4.1325993566156515e-05,42.5,54.28332380382144,31.303916931152344,0.9890235233399608,7.755574128343228,0.7283293283384793,9.472926980021695,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
1200000,2024-01-15T12:29:06,TeenyTinyLlama,7bb7327e-de45-43de-ade7-b55349bf386a,41791.25404930115,1.698660284322795,4.064631040549501e-05,42.5,51.781539471834236,31.303916931152344,0.49336812658839907,3.7911041539920083,0.3633175511266222,4.647789831707043,Germany,DEU,,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,,,83.47711181640625,machine,N,1.0
|
||||||
|
3
flax_model.msgpack
Normal file
3
flax_model.msgpack
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1b33cf403e27becf1f71e78ed8892b41f0d9f8c7475d3580146153eba4227c75
|
||||||
|
size 1872967607
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 3,
|
||||||
|
"do_sample": true,
|
||||||
|
"max_new_tokens": 1024,
|
||||||
|
"renormalize_logits": true,
|
||||||
|
"repetition_penalty": 1.2,
|
||||||
|
"temperature": 0.1,
|
||||||
|
"top_k": 50,
|
||||||
|
"top_p": 1.0,
|
||||||
|
"use_cache": true,
|
||||||
|
"transformers_version": "4.42.3"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:078f36ec1ce0fe3d3a0f246bad1f6b687a709feb2c162dccb805f4728ad13c77
|
||||||
|
size 1872982408
|
||||||
3
optimizer.bin
Normal file
3
optimizer.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b0bce02d56d28cae0c6d0b4cf38bcd4cc2d86833ad748762ccc138ca6fd7baec
|
||||||
|
size 3746099450
|
||||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e8ae0a6fbc3c3f195d41cc9b99715e07c166d96cf45600533493f4b6ee558964
|
||||||
|
size 1873028406
|
||||||
3
random_states_0.pkl
Normal file
3
random_states_0.pkl
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:53f958a32e8c34cd402f540f0fd9d70ad34bcb9f70a3c8e2e9daf05fc7500efb
|
||||||
|
size 14344
|
||||||
3
scheduler.bin
Normal file
3
scheduler.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:eee5d9f31e43eef75fd91050a9feebfec3b53026f0c02e9612943fa063263c15
|
||||||
|
size 1064
|
||||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"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
|
||||||
|
}
|
||||||
|
}
|
||||||
63147
tokenizer.json
Normal file
63147
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
51
tokenizer_config.json
Normal file
51
tokenizer_config.json
Normal file
@@ -0,0 +1,51 @@
|
|||||||
|
{
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"0": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"1": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"3": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"bos_token": "<s>",
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "</s>",
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"legacy": false,
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"pad_token": "<pad>",
|
||||||
|
"pad_token_id": 3,
|
||||||
|
"padding_side": "right",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"unk_token": "<unk>",
|
||||||
|
"unk_token_id": 0,
|
||||||
|
"use_default_system_prompt": false
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user