issues
search
IlyaGusev
/
rulm
Language modeling and instruction tuning for Russian
Apache License 2.0
450
stars
51
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Bump nltk from 3.8.1 to 3.9
#46
dependabot[bot]
opened
1 month ago
0
Yandex-gpt модели
#45
defdet
opened
3 months ago
0
Bump scikit-learn from 1.3.0 to 1.5.0
#44
dependabot[bot]
opened
3 months ago
0
How to use generate_instructions.py script?
#43
beybars1
opened
3 months ago
1
Bump transformers from 4.34.0 to 4.38.0
#42
dependabot[bot]
closed
5 months ago
1
Bump pillow from 10.2.0 to 10.3.0
#41
dependabot[bot]
closed
5 months ago
1
Qwen models
#40
Displacer
opened
6 months ago
1
convert_to_native.py 70b support
#39
Displacer
opened
6 months ago
0
Bump pillow from 10.0.1 to 10.2.0
#38
dependabot[bot]
closed
7 months ago
0
Bump transformers from 4.34.0 to 4.36.0
#37
dependabot[bot]
closed
5 months ago
1
Enhancements to Training Configurations and Script
#35
EvilFreelancer
closed
10 months ago
1
Двойной EOS-токен в скрипте генерации датасета
#34
hillenkoetter-ml
opened
11 months ago
0
small_fixes_imports_fp16_train
#33
RefalMachine
closed
11 months ago
1
LLaVA 7B/13B - Будущая русская GPT4V?
#32
NeuralAIM
opened
12 months ago
0
Bump pillow from 9.5.0 to 10.0.1
#31
dependabot[bot]
closed
11 months ago
0
Mistral 7B - лучше в русском чем saiga2_7b
#30
NeuralAIM
closed
12 months ago
1
Пример Collab файнтюн. Ошибка на этапе скачивания базовой модели.
#29
Sogl
closed
1 year ago
3
Проблема с режимами fine tuning
#28
eugenos-programos
opened
1 year ago
0
Проблема запуска ggml версии
#27
Samoed
closed
1 year ago
2
Модели путают склонения, падежи и т.д.
#26
NeuralAIM
opened
1 year ago
5
Feature remove wb
#25
ichrnkv
closed
1 year ago
0
Why results are much worse on V100?
#24
igroboy
closed
1 year ago
2
Воспроизведение результатов для Saiga2
#23
KNstntin
closed
1 year ago
2
Неправильно форматирование prompt'а?
#22
NeuralAIM
closed
1 year ago
2
Не удалось получить ожидаемые результаты при обучении
#21
Maphew93
closed
1 year ago
8
Is it possible to run under windows+ python + CUDA?
#20
blackcement
closed
1 year ago
3
I can't start, what is the error, please tell me
#19
blackcement
closed
1 year ago
2
Is there any way to increase speed?
#18
NikolayTV
closed
1 year ago
2
Rsg
#17
IlyaGusev
closed
1 year ago
0
Error while trying to train llama_13b following the guide
#16
Maphew93
closed
1 year ago
1
Bump transformers from 4.29.1 to 4.30.0
#11
dependabot[bot]
closed
1 year ago
1
Fine tuning with adapters
#9
helpau
closed
1 year ago
1
remove duplicated training_args
#8
poteminr
closed
1 year ago
3
fix mode to avoid referenced before assignment error
#7
poteminr
closed
1 year ago
1
Fune-tuning model with quantization
#6
anyaschenikova
closed
1 year ago
4
Posting issues rulm
#5
adarsh057
closed
1 year ago
0
Add missed param - "model_name"
#4
rakovskij-stanislav
closed
1 year ago
1
Update llama_13b_lora.json
#3
adarsh057
closed
1 year ago
1
Исправление "грамматическим" на "грамматичным"
#2
Koziev
closed
1 year ago
1
Razdel -> re in undup 2x speedup, fine grain blocks in LSH
#1
kuk
closed
1 year ago
0