Team Ai
Agents
Live
Problem
Plan
Sign
Petitions
Leaderboard
Community
Search
Create
Alerts
Model
public
Coding-With-Bashir
/
bwenge_ai
source
Hugging Face
updated 4mo ago
View on Hugging Face
0
likes
Like
Save
Clone
overview
files
community
commits
settings
root
file
.\.gitignore
447 B
download
file
.\configs\default.yaml
35 KB
download
file
.\configs\test_small.yaml
2 KB
download
file
.\data\processed_test\chat_data.jsonl
download
file
.\data\processed_test\instruction_data.jsonl
31.6 MB
download
file
.\data\processed_test\processing_summary.json
1 KB
download
file
.\data\processed_test\training_data.jsonl
169.5 MB
download
file
.\data\processed\.gitkeep
download
file
.\data\processed\chat_data.jsonl
download
file
.\data\processed\collection_summary.json
8 KB
download
file
.\data\processed\instruction_data.jsonl
107.2 MB
download
file
.\data\processed\processing_summary.json
7 KB
download
file
.\data\processed\training_data.jsonl
158.5 MB
download
file
.\data\raw_test\huggingface_mbazaNLP_Kinyarwanda_English_parallel_dataset.jsonl
12.0 MB
download
file
.\data\raw_test\huggingface_mbazaNLP_kinyarwanda_monolingual_v01.0.jsonl
185.1 MB
download
file
.\data\raw_test\huggingface_saillab_alpaca-kinyarwanda-cleaned.jsonl
31.6 MB
download
file
.\data\raw_test\huggingface\huggingface_summary.json
412 B
download
file
.\data\raw_test\huggingface\mbazaNLP_Kinyarwanda_English_parallel_dataset.jsonl
12.0 MB
download
file
.\data\raw_test\huggingface\mbazaNLP_Kinyarwanda_English_parallel_dataset.jsonl.done
5 B
download
file
.\data\raw_test\huggingface\mbazaNLP_kinyarwanda_monolingual_v01.0.jsonl
185.1 MB
download
file
.\data\raw_test\huggingface\mbazaNLP_kinyarwanda_monolingual_v01.0.jsonl.done
5 B
download
file
.\data\raw_test\huggingface\saillab_alpaca-kinyarwanda-cleaned.jsonl
31.6 MB
download
file
.\data\raw_test\huggingface\saillab_alpaca-kinyarwanda-cleaned.jsonl.done
5 B
download
file
.\data\raw\.gitkeep
download
file
.\data\raw\cc100_oscar\cc100_oscar_summary.json
91 B
download
file
.\data\raw\huggingface_ChrisToukmaji_kinyarwanda_instruction_tuning.jsonl
5.2 MB
download
file
.\data\raw\huggingface_CircuitNotion_kinyarwanda_corpus.jsonl
download
file
.\data\raw\huggingface_DigitalUmuganda_kinyarwanda-english-machine-translation-dataset.jsonl
download
file
.\data\raw\huggingface_DigitalUmuganda_NMT_Health_parallel_data_en_kin.jsonl
13.8 MB
download
file
.\data\raw\huggingface_DigitalUmuganda_NMT_Rwandan-Gazette_parallel_data_en_kin.jsonl
25.0 MB
download
file
.\data\raw\huggingface_jojo-ai-mst_Roleplay-Kinyarwanda.jsonl
3.0 MB
download
file
.\data\raw\huggingface_mbazaNLP_Kinyarwanda_English_parallel_dataset.jsonl
12.0 MB
download
file
.\data\raw\huggingface_michsethowusu_akan-kinyarwanda_sentence-pairs.jsonl
10.4 MB
download
file
.\data\raw\huggingface_michsethowusu_bambara-kinyarwanda_sentence-pairs.jsonl
9.6 MB
download
file
.\data\raw\huggingface_michsethowusu_bemba-kinyarwanda_sentence-pairs.jsonl
33.9 MB
download
file
.\data\raw\huggingface_michsethowusu_dinka-kinyarwanda_sentence-pairs.jsonl
7.2 MB
download
file
.\data\raw\huggingface_michsethowusu_dyula-kinyarwanda_sentence-pairs.jsonl
17.4 MB
download
file
.\data\raw\huggingface_michsethowusu_kinyarwanda-rundi_sentence-pairs.jsonl
77.9 MB
download
file
.\data\raw\huggingface_Mikecyane_Kinyarwanda_chat.jsonl
download
file
.\data\raw\huggingface_RogerB_kin_en_DigitalUmuganda.jsonl
5.0 MB
download
file
.\data\raw\huggingface_saillab_alpaca_kinyarwanda_taco.jsonl
173.5 MB
download
file
.\data\raw\huggingface_saillab_alpaca-kinyarwanda-cleaned.jsonl
31.6 MB
download
file
.\data\raw\huggingface_souvorinkg_english_kinyarwanda.jsonl
9.8 MB
download
file
.\data\raw\huggingface\ChrisToukmaji_kinyarwanda_instruction_tuning.jsonl
5.2 MB
download
file
.\data\raw\huggingface\ChrisToukmaji_kinyarwanda_instruction_tuning.jsonl.done
4 B
download
file
.\data\raw\huggingface\CircuitNotion_kinyarwanda_corpus.jsonl
download
file
.\data\raw\huggingface\DigitalUmuganda_kinyarwanda-english-machine-translation-dataset.jsonl
download
file
.\data\raw\huggingface\DigitalUmuganda_NMT_Health_parallel_data_en_kin.jsonl
13.8 MB
download
file
.\data\raw\huggingface\DigitalUmuganda_NMT_Rwandan-Gazette_parallel_data_en_kin.jsonl
25.0 MB
download
file
.\data\raw\huggingface\huggingface_summary.json
53 KB
download
file
.\data\raw\huggingface\jojo-ai-mst_Roleplay-Kinyarwanda.jsonl
3.0 MB
download
file
.\data\raw\huggingface\jojo-ai-mst_Roleplay-Kinyarwanda.jsonl.done
4 B
download
file
.\data\raw\huggingface\mbazaNLP_Kinyarwanda_English_parallel_dataset.jsonl
12.0 MB
download
file
.\data\raw\huggingface\mbazaNLP_Kinyarwanda_English_parallel_dataset.jsonl.done
5 B
download
file
.\data\raw\huggingface\michsethowusu_akan-kinyarwanda_sentence-pairs.jsonl
10.4 MB
download
file
.\data\raw\huggingface\michsethowusu_akan-kinyarwanda_sentence-pairs.jsonl.done
5 B
download
file
.\data\raw\huggingface\michsethowusu_bambara-kinyarwanda_sentence-pairs.jsonl
9.6 MB
download
file
.\data\raw\huggingface\michsethowusu_bambara-kinyarwanda_sentence-pairs.jsonl.done
5 B
download
file
.\data\raw\huggingface\michsethowusu_bemba-kinyarwanda_sentence-pairs.jsonl
33.9 MB
download
file
.\data\raw\huggingface\michsethowusu_bemba-kinyarwanda_sentence-pairs.jsonl.done
6 B
download
file
.\data\raw\huggingface\michsethowusu_dinka-kinyarwanda_sentence-pairs.jsonl
7.2 MB
download
file
.\data\raw\huggingface\michsethowusu_dinka-kinyarwanda_sentence-pairs.jsonl.done
5 B
download
file
.\data\raw\huggingface\michsethowusu_dyula-kinyarwanda_sentence-pairs.jsonl
17.4 MB
download
file
.\data\raw\huggingface\michsethowusu_dyula-kinyarwanda_sentence-pairs.jsonl.done
6 B
download
file
.\data\raw\huggingface\michsethowusu_kinyarwanda-rundi_sentence-pairs.jsonl
77.9 MB
download
file
.\data\raw\huggingface\Mikecyane_Kinyarwanda_chat.jsonl
download
file
.\data\raw\huggingface\RogerB_kin_en_DigitalUmuganda.jsonl
5.0 MB
download
file
.\data\raw\huggingface\RogerB_kin_en_DigitalUmuganda.jsonl.done
5 B
download
file
.\data\raw\huggingface\saillab_alpaca_kinyarwanda_taco.jsonl
173.5 MB
download
file
.\data\raw\huggingface\saillab_alpaca_kinyarwanda_taco.jsonl.done
5 B
download
file
.\data\raw\huggingface\saillab_alpaca-kinyarwanda-cleaned.jsonl
31.6 MB
download
file
.\data\raw\huggingface\saillab_alpaca-kinyarwanda-cleaned.jsonl.done
5 B
download
file
.\data\raw\huggingface\souvorinkg_english_kinyarwanda.jsonl
9.8 MB
download
file
.\data\raw\huggingface\souvorinkg_english_kinyarwanda.jsonl.done
5 B
download
file
.\data\raw\igihe_igihe_articles.jsonl
download
file
.\data\raw\igihe\igihe_articles.jsonl
download
file
.\data\raw\igihe\igihe_summary.json
436 B
download
file
.\data\raw\kigalitoday_kigalitoday_articles.jsonl
download
file
.\data\raw\kigalitoday\kigalitoday_articles.jsonl
download
file
.\data\raw\kigalitoday\kigalitoday_summary.json
263 B
download
file
.\data\raw\masakhane\masakhane_summary.json
76 B
download
file
.\data\raw\newtimes_rss_newtimes_rss_articles.jsonl
download
file
.\data\raw\newtimes_rss\newtimes_rss_articles.jsonl
download
file
.\data\raw\newtimes_rss\newtimes_rss_summary.json
238 B
download
file
.\data\raw\parallel\parallel_summary.json
85 B
download
file
.\data\raw\rbc_rbc_articles.jsonl
download
file
.\data\raw\rbc\rbc_articles.jsonl
download
file
.\data\raw\rbc\rbc_summary.json
145 B
download
file
.\data\raw\wikipedia_wikipedia_articles.jsonl
1.8 MB
download
file
.\data\raw\wikipedia\wikipedia_articles.jsonl
21.3 MB
download
file
.\data\raw\wikisource_wikisource_articles.jsonl
download
file
.\data\raw\wikisource\wikisource_articles.jsonl
download
file
.\data\raw\wikisource\wikisource_summary.json
166 B
download
file
.\data\raw\wiktionary_wiktionary_entries.jsonl
17 KB
download
file
.\data\raw\wiktionary\wiktionary_entries.jsonl
17 KB
download
file
.\data\raw\wiktionary\wiktionary_summary.json
172 B
download
file
.\desktop.ini
46 B
download
file
.\docs\data-collection.md
1 KB
download
file
.\docs\evaluation.md
386 B
download
file
.\docs\index.md
480 B
download
file
.\docs\training.md
684 B
download
file
.\pyproject.toml
1 KB
download
file
.\README.md
5 KB
download
file
.\scripts\collect_all.py
10 KB
download
file
.\scripts\collect_huggingface.py
3 KB
download
file
.\scripts\collect_wikipedia.py
5 KB
download
file
.\scripts\count_stats.py
18 KB
download
file
.\scripts\quick_process.py
1 KB
download
file
.\scripts\test_pipeline.py
5 KB
download
file
.\scripts\train.py
4 KB
download
file
.\src\__init__.py
75 B
download
file
.\src\bwenge_ai.egg-info\dependency_links.txt
1 B
download
file
.\src\bwenge_ai.egg-info\PKG-INFO
5 KB
download
file
.\src\bwenge_ai.egg-info\requires.txt
373 B
download
file
.\src\bwenge_ai.egg-info\SOURCES.txt
575 B
download
file
.\src\bwenge_ai.egg-info\top_level.txt
43 B
download
file
.\src\data_collection\__init__.py
download
file
.\src\data_collection\cc100_oscar_collector.py
7 KB
download
file
.\src\data_collection\data_processor.py
11 KB
download
file
.\src\data_collection\huggingface_collector.py
6 KB
download
file
.\src\data_collection\igihe_scraper.py
7 KB
download
file
.\src\data_collection\kigalitoday_scraper.py
6 KB
download
file
.\src\data_collection\masakhane_collector.py
6 KB
download
file
.\src\data_collection\parallel_corpus_collector.py
4 KB
download
file
.\src\data_collection\rbc_collector.py
4 KB
download
file
.\src\data_collection\rss_collector.py
4 KB
download
file
.\src\data_collection\web_utils.py
1 KB
download
file
.\src\data_collection\wikimedia_collector.py
8 KB
download
file
.\src\data_collection\wikipedia_collector.py
9 KB
download
file
.\src\evaluation\__init__.py
download
file
.\src\evaluation\metrics.py
11 KB
download
file
.\src\models\__init__.py
download
file
.\src\models\bwenge_model.py
5 KB
download
file
.\src\training\__init__.py
download
file
.\src\training\trainer.py
9 KB
download
file
.\tests\test_basic.py
6 KB
download
file
.gitattributes
4 KB
download
Coding-With-Bashir/bwenge_ai · main · files are served by the source, never re-hosted here