初始化项目,由ModelHub XC社区提供模型
Model: jerteh/gpt2-orao Source: Original Platform
This commit is contained in:
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
209
README.md
Normal file
209
README.md
Normal file
@@ -0,0 +1,209 @@
|
||||
---
|
||||
datasets:
|
||||
- jerteh/cc100-sr-jerteh
|
||||
- jerteh/SrpWiki
|
||||
- jerteh/SrpELTeC
|
||||
- srwac
|
||||
- procesaur/znanje
|
||||
language:
|
||||
- sr
|
||||
tags:
|
||||
- Srpski
|
||||
- Serbian
|
||||
- GPT2
|
||||
- generisanje
|
||||
license: cc-by-sa-4.0
|
||||
pipeline_tag: text-generation
|
||||
widget:
|
||||
- text: Kada bi čovek znao gde će pasti,
|
||||
- text: Jednom davno,
|
||||
- text: Srbija je
|
||||
- text: Najbolji lek za stres je
|
||||
---
|
||||
|
||||
|
||||
<h4><!--<i class="highlight-container"><b class="highlight">sr-gpt2-large</b></i> je sada -->
|
||||
|
||||
<i class="highlight-container"><b class="highlight">gpt2-orao</b></i> —
|
||||
Najveći generativni model za srpski jezik.</h4>
|
||||
|
||||
<img src="cover.png" class="cover">
|
||||
<div id="zastava">
|
||||
<div class="grb">
|
||||
<img src="https://www.ai.gov.rs/img/logo_60x120-2.png" style="position:relative; left:30px; z-index:10; height:85px">
|
||||
</div>
|
||||
<table width=100% style="border:0px">
|
||||
<tr style="background-color:#C6363C;width:100%;border:0px;height:30px"><td style="width:100vw"></td></tr>
|
||||
<tr style="background-color:#0C4076;width:100%;border:0px;height:30px"><td></td></tr>
|
||||
<tr style="background-color:#ffffff;width:100%;border:0px;height:30px"><td></td></tr>
|
||||
</table>
|
||||
</div>
|
||||
|
||||
|
||||
<ul style="font-weight:bold">
|
||||
<li>Generiše novi tekst, ili nastavlja započeti tekstualni unos</li>
|
||||
<li>Zasnovan na GPT2-large arhitekturi, 810 miliona parametara</li>
|
||||
<li>Obučavan na korpusu srpskog jezika veličine 4 milijarde tokena</li>
|
||||
<li>Jednaka podrška unosa i na ćirilici i na latinici!</li>
|
||||
</ul>
|
||||
|
||||
## Upotreba
|
||||
|
||||
```python
|
||||
>>> from transformers import pipeline, set_seed
|
||||
>>> generator = pipeline('text-generation', model='jerteh/gpt2-orao')
|
||||
>>> set_seed(23)
|
||||
>>> generator("", max_length=30, num_return_sequences=5)
|
||||
```
|
||||
|
||||
```
|
||||
[{'generated_text': 'Ja, međutim, ne idem na Adu - kaže Miodrag.'},
|
||||
{'generated_text': 'Domaćinstvo se nalazilo na mestu zvanom Kulina (ranije Kulina Vakuf) i bilo je jedno od najvećih i naj'},
|
||||
{'generated_text': 'Regionalne razlike se uglavnom odnose na geografski položaj, geografsko-geografski položaj i ekonomsku razvijenost.'},
|
||||
{'generated_text': 'Od tada do danas Srbija ne stoji na nogama'},
|
||||
{'generated_text': 'Iz tog razloga, na ovaj način se postiže bolja efikasnost rada, odnosno smanjuje se vreme potrebno za sprovođenje simulacije.'}]
|
||||
```
|
||||
|
||||
Pored navedenih, model je obučavan i na ostalim korpusima [Društva za jezičke resurse i tehnologije](https://jerteh.rs),
|
||||
uključujući korpuse savremenog srpskog jezika: SrpKor2013 i SrpKor2021,
|
||||
kao i korpus [PDRS 1.0](https://www.clarin.si/repository/xmlui/handle/11356/1752) razvijen od strane Instituta za Srpski jezik SANU.
|
||||
|
||||
<h4>U slučaju potrebe za manjim modelom, pogledajte <a href="https://huggingface.co/jerteh/gpt2-vrabac" class="highlight-container">
|
||||
<b class="highlight">gpt2-vrabac</b></a> — manji model obučen na istom korpusu.</h4>
|
||||
|
||||
<div class="inline-flex flex-col" style="line-height: 1.5;padding-right:40px">
|
||||
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">Autor</div>
|
||||
<a href="https://huggingface.co/procesaur">
|
||||
<div class="flex">
|
||||
<div
|
||||
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%;
|
||||
background-size: cover; background-image: url('https://cdn-uploads.huggingface.co/production/uploads/1673534533167-63bc254fb8c61b8aa496a39b.jpeg?w=200&h=200&f=face')">
|
||||
</div>
|
||||
</div>
|
||||
</a>
|
||||
<div style="text-align: center; font-size: 16px; font-weight: 800">Mihailo Škorić</div>
|
||||
<div>
|
||||
<a href="https://huggingface.co/procesaur">
|
||||
<div style="text-align: center; font-size: 14px;">@procesaur</div>
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="inline-flex flex-col" style="line-height: 1.5;padding-right:40px">
|
||||
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">Computation</div>
|
||||
<a href="https://www.ai.gov.rs/">
|
||||
<div class="flex">
|
||||
<div
|
||||
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%;
|
||||
background-size: contain; background-image: url(https://www.ai.gov.rs/img/logo_60x120-2.png);background-repeat: no-repeat;
|
||||
background-position: center;">
|
||||
</div>
|
||||
</div>
|
||||
</a>
|
||||
<div style="text-align: center; font-size: 16px; font-weight: 800" title="nVidia DGX-zasnovan sistem">Nacionalna AI platforma</div>
|
||||
<div>
|
||||
<a href="https://www.ai.gov.rs/">
|
||||
<div style="text-align: center; font-size: 14px;">ai.gov.rs</div>
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="inline-flex flex-col" style="line-height: 1.5;padding-right:40px">
|
||||
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">Data</div>
|
||||
<a href="https://jerteh.rs/">
|
||||
<div class="flex">
|
||||
<div
|
||||
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%;
|
||||
background-size: contain; background-image: url(https://cdn-avatars.huggingface.co/v1/production/uploads/1673601491672-63bc254fb8c61b8aa496a39b.png?w=200&h=200&f=face);background-repeat: no-repeat;
|
||||
background-position: center;">
|
||||
</div>
|
||||
</div>
|
||||
</a>
|
||||
<div style="text-align: center; font-size: 16px; font-weight: 800" title="Društvo za jezičke resurse i tehnologije">JeRTeh</div>
|
||||
<div>
|
||||
<a href="https://huggingface.co/jerteh">
|
||||
<div style="text-align: center; font-size: 14px;">@jerteh</div>
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
## Citiranje
|
||||
|
||||
```bibtex
|
||||
@article{skoric24modeli,
|
||||
author = {Mihailo \vSkori\'c},
|
||||
title = {Novi jezi\vcki modeli za srpski jezik},
|
||||
journal = {Infoteka},
|
||||
volume = {24},
|
||||
issue = {1},
|
||||
year = {2024},
|
||||
publisher = {Zajednica biblioteka univerziteta u Srbiji, Beograd},
|
||||
url = {https://arxiv.org/abs/2402.14379}
|
||||
}
|
||||
```
|
||||
|
||||
<style>
|
||||
.ffeat: {
|
||||
color:red
|
||||
}
|
||||
|
||||
.cover {
|
||||
width: 100%;
|
||||
margin-bottom: 5pt
|
||||
}
|
||||
|
||||
.highlight-container, .highlight {
|
||||
position: relative;
|
||||
text-decoration:none
|
||||
}
|
||||
|
||||
.highlight-container {
|
||||
display: inline-block;
|
||||
|
||||
}
|
||||
|
||||
.highlight{
|
||||
color:white;
|
||||
text-transform:uppercase;
|
||||
font-size: 16pt;
|
||||
}
|
||||
|
||||
.highlight-container{
|
||||
padding:5px 10px
|
||||
}
|
||||
|
||||
.highlight-container:before {
|
||||
content: " ";
|
||||
display: block;
|
||||
height: 100%;
|
||||
width: 100%;
|
||||
margin-left: 0px;
|
||||
margin-right: 0px;
|
||||
position: absolute;
|
||||
background: #e80909;
|
||||
transform: rotate(2deg);
|
||||
top: -1px;
|
||||
left: -1px;
|
||||
border-radius: 20% 25% 20% 24%;
|
||||
padding: 10px 18px 18px 10px;
|
||||
}
|
||||
|
||||
div.grb, #zastava>table {
|
||||
position:absolute;
|
||||
top:0px;
|
||||
left: 0px;
|
||||
margin:0px
|
||||
}
|
||||
|
||||
div.grb>img, #zastava>table{
|
||||
margin:0px
|
||||
}
|
||||
|
||||
#zastava {
|
||||
position: relative;
|
||||
margin-bottom:120px
|
||||
}
|
||||
</style>
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 0,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 0,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 1280,
|
||||
"n_head": 20,
|
||||
"n_inner": null,
|
||||
"n_layer": 36,
|
||||
"n_positions": 1024,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"task_specific_params": {
|
||||
"text-generation": {
|
||||
"do_sample": true,
|
||||
"max_length": 50
|
||||
}
|
||||
},
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.27.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.27.4"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4ab52c5a1d4a6b9b554ff8fa95fd83ded870d195e5d12a616b09787df26fb66c
|
||||
size 3128264752
|
||||
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:ca95f294a01c6517ae297acc9026edceba13cdcf0ac4464774087adb88355414
|
||||
size 3128377405
|
||||
98557
tokenizer.json
Normal file
98557
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
34848
trainer_state.json
Normal file
34848
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user